Role

We’re looking for a Principal Software Development Engineer to join our team. Based out of our Bangalore office, you will report to the Senior Manager, Software Engineering within the Zero Trust Exchange department.

As a Principal Software Engineer you will build the backend systems that keep the product fast, reliable, and able to scale as usage grows. You will create microservices and event-driven workflows, and ensure data can be ingested and queried efficiently across relational, graph, and time-series databases. You will also drive cross-team execution by collaborating closely with multiple groups to deliver high-quality results on tight timelines.

What you’ll do (Role Expectations)

• Architect and deliver scalable microservices on EKS (GoLang): design, build, and operate production services that meet uptime, latency, and scale goals
• Build event-driven pipelines with Kafka and MQTT: implement asynchronous workflows that are resilient, observable, and easy to evolve as product needs change
• Design high-performance data models and access patterns: optimize ingest and querying across RDS MySQL, Neo4J, and ElasticSearch for correctness, speed, and cost efficiency
• Harden production readiness and operational excellence: establish monitoring, alerting, tracing, and on-call standards; drive root-cause fixes and reliability improvements
• Lead cross-team delivery and technical direction: align stakeholders, break down complex work, and execute quickly while maintaining a high bar for quality and security

Who You Are (Success Profile)

• You act like an owner. Your passion for the mission fuels your bias for action. You operate with integrity because you genuinely care about the outcome. You adapt to what’s needed, navigating seamlessly between high-level strategy and hands-on execution.
• You are a problem-solver. You seek out challenges because you are energized by finding solutions, knowing that solving the hard problems delivers the biggest impact.
• You are a positive force. You approach hard problems with constructive energy and a 'can-do' spirit that is contagious, inspiring your team to stay focused on the solution.
• You are a pragmatic builder. You are obsessed with creating, iterating, and shipping. You aren't afraid to roll up your sleeves and build the first version yourself, balancing the drive for technical excellence with the need to deliver value to users quickly.
• You champion simplicity. You are skilled at distilling complex problems, user needs, and technical concepts into clear, simple, and actionable plans. You are a precise communicator who brings clarity and focus to every interaction.

What We’re Looking for (Minimum Qualifications)

• Senior-level backend engineering experience designing and shipping highly scalable microservices in production developed in Go
• Proven experience with event-driven, asynchronous architectures using messaging/streaming platforms such as Kafka
• Strong data engineering and persistence skills building efficient ingest and query patterns across relational databases (MySQL) plus at least one of ElasticSearch or Neo4J
• Hands-on experience running services on Kubernetes (ideally EKS), including deployment, troubleshooting, and operational ownership

What Will Make You Stand Out (Preferred Qualifications)

• Proven ability to profile and optimize distributed systems end-to-end (latency, throughput, resource usage), including performance tuning across services, databases, and messaging
• Strong track record designing debuggability/observability for distributed applications—structured logging, metrics, distributed tracing, and actionable dashboards/alerts for rapid incident triage
• Experience defining and operationalizing SLIs/SLOs (error budgets, alert policies, reliability reporting) and driving product decisions based on measured service health

#LI-Hybrid #LI-NT1

Why This Role Matters 

This role powers Tekion’s AI‑native, end‑to‑end automotive platform by turning unified dealership data across DMS, CRM, Digital Retail, Service, and Payments into real‑time intelligence. You’ll operationalize a graph‑based contextual ecosystem so agents can retrieve the right context, enforce policy, and personalize experiences that drive measurable dealer outcomes. You’ll also build the resilient control layer - MCP and the LLM Gateway - that enables safe, cost‑efficient, multi‑provider LLM usage. Finally, you’ll define the standards for building, evaluating, deploying, and governing agentic systems so product teams can ship AI features quickly, safely, and at scale. In addition to enabling agentic systems powered by LLMs, this role also drives building the platform for classical ML models driving optimization across dealership operations.  

What Makes This Opportunity Unique 

This role offers direct, measurable impact on dealer outcomes and consumer experiences across Tekion’s Automotive Retail Cloud and Automotive Enterprise Cloud, with end‑to‑end ownership of an LLM control plane and gateway that serve multi‑tenant workloads under SLAs and, quality and cost guardrails. You’ll leverage a rich vertical dataset and domain graph spanning sales, service, parts, F&I, accounting, and consumer touchpoints to power context‑aware agents and retrieval‑augmented generation. You’ll also shape core levers - agent orchestration patterns, evaluation frameworks, and safety guardrails - so improvements in latency, reliability, evaluation quality, and safety translate into dealer KPIs like upsell, cycle time, CSAT, and service revenue.  You’ll also maintain and enhance the platform to support classical supervised and unsupervised ML models . 

Responsibilities 

• Build and run the LLM control plane/gateway: smart routing, rate limits/quotas, failover, and token/cost tracking. 

• Ship a unified API and SDKs (REST/gRPC) with normalized schemas, structured outputs, caching, and full observability (traces/logs/metrics). 

• Enforce safety and privacy by default: content filtering, prompt/response validation, and PII redaction. 

• Enable multi‑model, multi‑vendor use LLMs with automated canarying and versioning. 

• Own the agent runtime: tool registry, permissions, function calling, grounding, and retrieval. 

• Design orchestration patterns (sequential, planner‑executor, streaming) and manage agent state and long‑running workflows. 

• Enabling platform components for training and scoring pipelines for classical ML (e.g., XGBoost/LightGBM/linear/trees) and deep models; standardize experiment tracking and packaging. 

• Create components to Monitor model and data drift, retraining and tuning models as needed to maintain accuracy and relevance. 

• Add human‑in‑the‑loop review and safe‑actioning before agents touch dealer systems. 

• Evolve the domain graph and entity resolution; build reliable data ingestion pipelines. 

• Serve real‑time context to agents (profiles, inventory, pricing, appointments, service history) with access controls and lineage. 

• Power retrieval with hybrid search (graph + vector + keyword) and smart cache/TTL to balance accuracy, latency, and cost. 

• Run continuous offline/online evaluations for quality, factuality, bias, and safety for the platform sanity. 

• Define SLOs for latency (p50/p95), uptime, and cost view capabilities; enable autoscaling and spend controls. 

• Maintain a model/agent registry, versioning, approvals, audit trails, and reproducibility; support compliances where needed. 

• Provide templates/CLIs, sandboxes, and docs so product teams can build and ship fast; mentor engineers and champion MLOps and AI safety best practices. 

Desired Skills & Experience 

• 12–15+ years building large‑scale data/ML or platform systems; strong software engineering fundamentals (Abstracted API design, concurrency, distributed systems). 

• Production experience with Python plus one of Java/Scala/Go; microservices and API design. 

• MLOps at scale: pipelines (Airflow/Kubeflow), tracking/registry (MLflow), CI/CD for models, A/B testing, shadow/canary, and online feature computation (Spark/Flink/Kafka). 

• Cloud and containers: AWS (preferred), plus Docker/Kubernetes; performance, reliability, and cost engineering in multi‑tenant SaaS. 

• Practical ML knowledge (feature engineering, training, evaluation, drift detection); experience deploying models that power user‑facing workflows. 

• Built or operated an LLM gateway/control plane: provider adapters, routing/policies, caching, quota/rate‑limit, cost and token accounting. 

• Agentic systems: tool use/function calling, orchestration frameworks, human‑in‑the‑loop, safety/guardrails, and online evaluation/telemetry. 

• Graph and retrieval: knowledge graphs (e.g., Neo4j/Neptune/TigerGraph), GraphQL, vector search (e.g., pgvector/Qdrant/Milvus), hybrid retrieval patterns. 

Preferred Mindset 

• Platform‑as‑product: obsess over developer experience, paved roads, and clear SLAs. 

• Thinks in systems - observability, fallback, access control are core, not afterthoughts. 

• Passionate about AI - enjoys enabling real-world LLM and agentic use cases. 

• Cost‑aware builder: you treat latency and dollars as first‑class metrics and design for graceful degradation. 

• Vendor‑agnostic thinker: choose the right model/provider per use case; build for portability and resilience. 

• Documentation and teaching: you make complex systems understandable; you uplevel teams. 

Opportunity

Get Well is seeking an experienced and highly motivated Staff Data Software Engineer to help build and optimize our cloud-native data platform that powers AI, analytics, and clinical applications. You will play a key role in developing scalable, compliant data infrastructure and pipelines designed specifically for the healthcare domain, while mentoring junior engineers and leading cross-functional initiatives to drive innovation.

This is a hands-on engineering role suitable for someone who thrives at the intersection of modern data engineering, cloud-native platforms, DevOps, healthcare data, and AI enablement.  Candidates must have hands-on software development experience with at least one healthcare company—preferably in the provider space—with exposure to EHRs and core healthcare data domains.

Responsibilities

Data Engineering & Platform Development

• Design, build, and maintain scalable data pipelines supporting batch and real-time use cases.
• Develop and maintain production-grade data workflows that move and transform sensitive healthcare data across distributed systems at scale.
• Work with Spark, Databricks, Airflow/Temporal, and dbt to ingest, process, and manage structured and unstructured data.
• Design and implement reusable, efficient data models for analytics and AI/ML use cases.
• Ensure platform resiliency using CI/CD pipelines, observability tools, and logging frameworks.
• Leverage Infrastructure as Code practices using Terraform, CloudFormation, or equivalent to manage cloud resources.

Healthcare Data Integration & Compliance

• Ingest and normalize complex healthcare data sets (FHIR, HL7, CCDA, Claims, EDI, Epic/Clarity, etc.).
• Familiarity with clinical coding systems and ontologies, such as ICD-10, SNOMED CT, LOINC, or RxNorm.
• Collaborate with compliance and security teams to ensure adherence to HIPAA, GDPR, and internal controls.
• Implement fine-grained access control, encryption at rest and in transit, audit logging, and data lineage strategies.

AI & GenAI Enablement

• Work alongside AI/ML and data science teams to build pipelines feeding predictive and generative models.
• Tune data infrastructure for performance across distributed systems and hybrid data stores like SQL, MongoDB, ClickHouse.
• Prioritize scalability and flexibility in designing LLM-compatible pipelines and use GenAI best practices for healthcare use cases.
• Utilize Spark clusters and query frameworks such as SparkSQL and SPARQL for large-scale data access.
• Utilize and manage graph databases (e.g., Neo4j, Amazon Neptune, or similar) to support complex relationship modeling and healthcare data connectivity use cases.
• Enable high-quality training data pipelines and implement feature stores and model serving systems.

Data Governance, Quality & Monitoring

• Implement data quality frameworks and establish robust validation processes using tools such as Great Expectations or equivalent.
• Build automated anomaly detection tools for data drift and integrity checks.
• Support data cataloging, metadata management, and ensure consistent documentation across datasets.

Collaboration, Mentorship & Leadership

• Act as a mentor to junior engineers through code reviews, paired programming, and technical guidance.
• Lead cross-functional projects with teams including clinical informatics, architecture, security, product, and design.
• Contribute to and enforce data engineering best practices, patterns, and platform standardization.

Learning and Innovation

• Research and evaluate emerging tools and frameworks (e.g., Apache Iceberg, Delta Lake) for incorporation into the platform.
• Proactively identify opportunities to improve architecture and leverage evolving trends in GenAI and cloud-native computing.

Qualifications

Education & Experience

• Bachelor’s or Master’s degree in Computer Science, Engineering, or related field.
• 8–12 years of experience in software or data engineering roles including at least 3 years working with large-scale or cloud-native data systems.
• Must have prior software development experience in the healthcare domain—including payers, providers, health tech, medical devices, or life sciences.
• Functional knowledge and direct experience with healthcare data types (FHIR, HL7, Claims, EDI, Epic/Clarity, etc.).
• Demonstrated experience in designing, implementing, and maintaining data pipelines that move and transform healthcare data with production-level quality, reliability, and performance.

Technical Skills

• Advanced programming experience in Python, SQL, and distributed processing with Apache Spark.
• Cloud-native platform experience with Azure.
• Proven capability with Infrastructure as Code (Terraform, CloudFormation) strongly preferred.
• Experience with data warehouses and lakes including Snowflake, Databricks, and ClickHouse.
• Familiarity working with GenAI tools and ML pipelines in production environments.
• Strong skills in data modeling, job orchestration (Airflow), data transformation (dbt), and pipeline optimization.
• Experience with DevOps/tooling stacks for CI/CD, containerization, observability, and cost optimization.
• Familiarity with data validation and anomaly detection tools such as Great Expectations.
• Experience with SparkSQL and SPARQL is a plus.

Professional Attributes

• Excellent communication and collaboration skills across cross-functional, domain, and technical stakeholders.
• Ability to lead initiatives and drive data engineering standards.
• Self-driven, with a commitment to delivering high-quality solutions in regulated and sensitive environments.

About GW RhythmX

GW RhythmX is revolutionizing healthcare through connected, AI-native intelligence that unites clinical insight, patient engagement, and system-wide care orchestration. The company combines market-leading AI precision care technology with extensive trusted patient engagement leadership to help health systems deliver the right care, at the right time, through the right clinician and channel. Its solutions are deployed across more than 150 health systems, touching more than 85M patients including 8M U.S. military veterans. The company's award-winning solutions were recognized again in 2024 by KLAS Research, Fierce Healthcare, and AVIA Marketplace. A SymphonyAI Group company, GW RhythmX leverages various firm assets, including $1B+ in R&D investment, longitudinal data related to 300 million patients, 4.4 billion total annual claims, and 1.8 million healthcare professionals at more than 3,000 facilities globally.

GW RhythmX  is proud to be an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age or veteran status.

Senior Software Engineer  -  Senior Machine Learning Platform

Why This Role Matters 

This role powers Tekion’s AI‑native, end‑to‑end automotive platform by turning unified dealership data across DMS, CRM, Digital Retail, Service, and Payments into real‑time intelligence. You’ll operationalize a graph‑based contextual ecosystem so agents can retrieve the right context, enforce policy, and personalize experiences that drive measurable dealer outcomes. You’ll also build the resilient control layer - MCP and the LLM Gateway - that enables safe, cost‑efficient, multi‑provider LLM usage. Finally, you’ll define the standards for building, evaluating, deploying, and governing agentic systems so product teams can ship AI features quickly, safely, and at scale. In addition to enabling agentic systems powered by LLMs, this role also drives building the platform for classical ML models driving optimization across dealership operations.  

What Makes This Opportunity Unique 

This role offers direct, measurable impact on dealer outcomes and consumer experiences across Tekion’s Automotive Retail Cloud and Automotive Enterprise Cloud, with end‑to‑end ownership of an LLM control plane and gateway that serve multi‑tenant workloads under SLAs and, quality and cost guardrails. You’ll leverage a rich vertical dataset and domain graph spanning sales, service, parts, F&I, accounting, and consumer touchpoints to power context‑aware agents and retrieval‑augmented generation. You’ll also shape core levers - agent orchestration patterns, evaluation frameworks, and safety guardrails - so improvements in latency, reliability, evaluation quality, and safety translate into dealer KPIs like upsell, cycle time, CSAT, and service revenue.  You’ll also maintain and enhance the platform to support classical supervised and unsupervised ML models . 

Responsibilities 

• Build and run the LLM control plane/gateway: smart routing, rate limits/quotas, failover, and token/cost tracking. 

• Ship a unified API and SDKs (REST/gRPC) with normalized schemas, structured outputs, caching, and full observability (traces/logs/metrics). 

• Enforce safety and privacy by default: content filtering, prompt/response validation, and PII redaction. 

• Enable multi‑model, multi‑vendor use LLMs with automated canarying and versioning. 

• Own the agent runtime: tool registry, permissions, function calling, grounding, and retrieval. 

• Design orchestration patterns (sequential, planner‑executor, streaming) and manage agent state and long‑running workflows. 

• Enabling platform components for training and scoring pipelines for classical ML (e.g., XGBoost/LightGBM/linear/trees) and deep models; standardize experiment tracking and packaging. 

• Create components to Monitor model and data drift, retraining and tuning models as needed to maintain accuracy and relevance. 

• Add human‑in‑the‑loop review and safe‑actioning before agents touch dealer systems. 

• Evolve the domain graph and entity resolution; build reliable data ingestion pipelines. 

• Serve real‑time context to agents (profiles, inventory, pricing, appointments, service history) with access controls and lineage. 

• Power retrieval with hybrid search (graph + vector + keyword) and smart cache/TTL to balance accuracy, latency, and cost. 

• Run continuous offline/online evaluations for quality, factuality, bias, and safety for the platform sanity. 

• Define SLOs for latency (p50/p95), uptime, and cost view capabilities; enable autoscaling and spend controls. 

• Maintain a model/agent registry, versioning, approvals, audit trails, and reproducibility; support compliances where needed. 

• Provide templates/CLIs, sandboxes, and docs so product teams can build and ship fast; mentor engineers and champion MLOps and AI safety best practices. 

Desired Skills & Experience 

• 5 - 7 years building large‑scale data/ML or platform systems; strong software engineering fundamentals (Abstracted API design, concurrency, distributed systems). 

• Production experience with Python plus one of Java/Scala/Go; microservices and API design. 

• MLOps at scale: pipelines (Airflow/Kubeflow), tracking/registry (MLflow), CI/CD for models, A/B testing, shadow/canary, and online feature computation (Spark/Flink/Kafka). 

• Cloud and containers: AWS (preferred), plus Docker/Kubernetes; performance, reliability, and cost engineering in multi‑tenant SaaS. 

• Practical ML knowledge (feature engineering, training, evaluation, drift detection); experience deploying models that power user‑facing workflows. 

• Built or operated an LLM gateway/control plane: provider adapters, routing/policies, caching, quota/rate‑limit, cost and token accounting. 

• Agentic systems: tool use/function calling, orchestration frameworks, human‑in‑the‑loop, safety/guardrails, and online evaluation/telemetry. 

• Graph and retrieval: knowledge graphs (e.g., Neo4j/Neptune/TigerGraph), GraphQL, vector search (e.g., pgvector/Qdrant/Milvus), hybrid retrieval patterns. 

Preferred Mindset 

• Platform‑as‑product: obsess over developer experience, paved roads, and clear SLAs. 

• Thinks in systems - observability, fallback, access control are core, not afterthoughts. 

• Passionate about AI - enjoys enabling real-world LLM and agentic use cases. 

• Cost‑aware builder: you treat latency and dollars as first‑class metrics and design for graceful degradation. 

• Vendor‑agnostic thinker: choose the right model/provider per use case; build for portability and resilience. 

• Documentation and teaching: you make complex systems understandable; you uplevel teams. 

Why This Role Matters 

This role powers Tekion’s AI‑native, end‑to‑end automotive platform by turning unified dealership data across DMS, CRM, Digital Retail, Service, and Payments into real‑time intelligence. You’ll operationalize a graph‑based contextual ecosystem so agents can retrieve the right context, enforce policy, and personalize experiences that drive measurable dealer outcomes. You’ll also build the resilient control layer - MCP and the LLM Gateway - that enables safe, cost‑efficient, multi‑provider LLM usage. Finally, you’ll define the standards for building, evaluating, deploying, and governing agentic systems so product teams can ship AI features quickly, safely, and at scale. In addition to enabling agentic systems powered by LLMs, this role also drives building the platform for classical ML models driving optimization across dealership operations.  

What Makes This Opportunity Unique 

This role offers direct, measurable impact on dealer outcomes and consumer experiences across Tekion’s Automotive Retail Cloud and Automotive Enterprise Cloud, with end‑to‑end ownership of an LLM control plane and gateway that serve multi‑tenant workloads under SLAs and, quality and cost guardrails. You’ll leverage a rich vertical dataset and domain graph spanning sales, service, parts, F&I, accounting, and consumer touchpoints to power context‑aware agents and retrieval‑augmented generation. You’ll also shape core levers - agent orchestration patterns, evaluation frameworks, and safety guardrails - so improvements in latency, reliability, evaluation quality, and safety translate into dealer KPIs like upsell, cycle time, CSAT, and service revenue.  You’ll also maintain and enhance the platform to support classical supervised and unsupervised ML models . 

Responsibilities 

• Build and run the LLM control plane/gateway: smart routing, rate limits/quotas, failover, and token/cost tracking. 

• Ship a unified API and SDKs (REST/gRPC) with normalized schemas, structured outputs, caching, and full observability (traces/logs/metrics). 

• Enforce safety and privacy by default: content filtering, prompt/response validation, and PII redaction. 

• Enable multi‑model, multi‑vendor use LLMs with automated canarying and versioning. 

• Own the agent runtime: tool registry, permissions, function calling, grounding, and retrieval. 

• Design orchestration patterns (sequential, planner‑executor, streaming) and manage agent state and long‑running workflows. 

• Enabling platform components for training and scoring pipelines for classical ML (e.g., XGBoost/LightGBM/linear/trees) and deep models; standardize experiment tracking and packaging. 

• Create components to Monitor model and data drift, retraining and tuning models as needed to maintain accuracy and relevance. 

• Add human‑in‑the‑loop review and safe‑actioning before agents touch dealer systems. 

• Evolve the domain graph and entity resolution; build reliable data ingestion pipelines. 

• Serve real‑time context to agents (profiles, inventory, pricing, appointments, service history) with access controls and lineage. 

• Power retrieval with hybrid search (graph + vector + keyword) and smart cache/TTL to balance accuracy, latency, and cost. 

• Run continuous offline/online evaluations for quality, factuality, bias, and safety for the platform sanity. 

• Define SLOs for latency (p50/p95), uptime, and cost view capabilities; enable autoscaling and spend controls. 

• Maintain a model/agent registry, versioning, approvals, audit trails, and reproducibility; support compliances where needed. 

Desired Skills & Experience 

• 4 - 5+ years building large‑scale data/ML or platform systems; strong software engineering fundamentals (Abstracted API design, concurrency, distributed systems). 

• Production experience with Python plus one of Java/Scala/Go; microservices and API design. 

• MLOps at scale: pipelines (Airflow/Kubeflow), tracking/registry (MLflow), CI/CD for models, A/B testing, shadow/canary, and online feature computation (Spark/Flink/Kafka). 

• Cloud and containers: AWS (preferred), plus Docker/Kubernetes; performance, reliability, and cost engineering in multi‑tenant SaaS. 

• Practical ML knowledge (feature engineering, training, evaluation, drift detection); experience deploying models that power user‑facing workflows. 

• Built or operated an LLM gateway/control plane: provider adapters, routing/policies, caching, quota/rate‑limit, cost and token accounting. 

• Agentic systems: tool use/function calling, orchestration frameworks, human‑in‑the‑loop, safety/guardrails, and online evaluation/telemetry. 

• Graph and retrieval: knowledge graphs (e.g., Neo4j/Neptune/TigerGraph), GraphQL, vector search (e.g., pgvector/Qdrant/Milvus), hybrid retrieval patterns. 

Preferred Mindset 

• Platform‑as‑product: obsess over developer experience, paved roads, and clear SLAs. 

• Thinks in systems - observability, fallback, access control are core, not afterthoughts. 

• Passionate about AI - enjoys enabling real-world LLM and agentic use cases. 

• Cost‑aware builder: you treat latency and dollars as first‑class metrics and design for graceful degradation. 

• Vendor‑agnostic thinker: choose the right model/provider per use case; build for portability and resilience. 

Why This Role Matters 

This role powers Tekion’s AI‑native, end‑to‑end automotive platform by turning unified dealership data across DMS, CRM, Digital Retail, Service, and Payments into real‑time intelligence. You’ll operationalize a graph‑based contextual ecosystem so agents can retrieve the right context, enforce policy, and personalize experiences that drive measurable dealer outcomes. You’ll also build the resilient control layer - MCP and the LLM Gateway - that enables safe, cost‑efficient, multi‑provider LLM usage. Finally, you’ll define the standards for building, evaluating, deploying, and governing agentic systems so product teams can ship AI features quickly, safely, and at scale. In addition to enabling agentic systems powered by LLMs, this role also drives building the platform for classical ML models driving optimization across dealership operations.  

What Makes This Opportunity Unique 

This role offers direct, measurable impact on dealer outcomes and consumer experiences across Tekion’s Automotive Retail Cloud and Automotive Enterprise Cloud, with end‑to‑end ownership of an LLM control plane and gateway that serve multi‑tenant workloads under SLAs and, quality and cost guardrails. You’ll leverage a rich vertical dataset and domain graph spanning sales, service, parts, F&I, accounting, and consumer touchpoints to power context‑aware agents and retrieval‑augmented generation. You’ll also shape core levers - agent orchestration patterns, evaluation frameworks, and safety guardrails - so improvements in latency, reliability, evaluation quality, and safety translate into dealer KPIs like upsell, cycle time, CSAT, and service revenue.  You’ll also maintain and enhance the platform to support classical supervised and unsupervised ML models . 

Responsibilities 

• Build and run the LLM control plane/gateway: smart routing, rate limits/quotas, failover, and token/cost tracking. 

• Ship a unified API and SDKs (REST/gRPC) with normalized schemas, structured outputs, caching, and full observability (traces/logs/metrics). 

• Enforce safety and privacy by default: content filtering, prompt/response validation, and PII redaction. 

• Enable multi‑model, multi‑vendor use LLMs with automated canarying and versioning. 

• Own the agent runtime: tool registry, permissions, function calling, grounding, and retrieval. 

• Design orchestration patterns (sequential, planner‑executor, streaming) and manage agent state and long‑running workflows. 

• Enabling platform components for training and scoring pipelines for classical ML (e.g., XGBoost/LightGBM/linear/trees) and deep models; standardize experiment tracking and packaging. 

• Create components to Monitor model and data drift, retraining and tuning models as needed to maintain accuracy and relevance. 

• Add human‑in‑the‑loop review and safe‑actioning before agents touch dealer systems. 

• Evolve the domain graph and entity resolution; build reliable data ingestion pipelines. 

• Serve real‑time context to agents (profiles, inventory, pricing, appointments, service history) with access controls and lineage. 

• Power retrieval with hybrid search (graph + vector + keyword) and smart cache/TTL to balance accuracy, latency, and cost. 

• Run continuous offline/online evaluations for quality, factuality, bias, and safety for the platform sanity. 

• Define SLOs for latency (p50/p95), uptime, and cost view capabilities; enable autoscaling and spend controls. 

• Maintain a model/agent registry, versioning, approvals, audit trails, and reproducibility; support compliances where needed. 

• Provide templates/CLIs, sandboxes, and docs so product teams can build and ship fast; mentor engineers and champion MLOps and AI safety best practices. 

Desired Skills & Experience 

• 5+ - 8+ years building large‑scale data/ML or platform systems; strong software engineering fundamentals (Abstracted API design, concurrency, distributed systems). 

• Production experience with Python plus one of Java/Scala/Go; microservices and API design. 

• MLOps at scale: pipelines (Airflow/Kubeflow), tracking/registry (MLflow), CI/CD for models, A/B testing, shadow/canary, and online feature computation (Spark/Flink/Kafka). 

• Cloud and containers: AWS (preferred), plus Docker/Kubernetes; performance, reliability, and cost engineering in multi‑tenant SaaS. 

• Practical ML knowledge (feature engineering, training, evaluation, drift detection); experience deploying models that power user‑facing workflows. 

• Built or operated an LLM gateway/control plane: provider adapters, routing/policies, caching, quota/rate‑limit, cost and token accounting. 

• Agentic systems: tool use/function calling, orchestration frameworks, human‑in‑the‑loop, safety/guardrails, and online evaluation/telemetry. 

• Graph and retrieval: knowledge graphs (e.g., Neo4j/Neptune/TigerGraph), GraphQL, vector search (e.g., pgvector/Qdrant/Milvus), hybrid retrieval patterns. 

Preferred Mindset 

• Platform‑as‑product: obsess over developer experience, paved roads, and clear SLAs. 

• Thinks in systems - observability, fallback, access control are core, not afterthoughts. 

• Passionate about AI - enjoys enabling real-world LLM and agentic use cases. 

• Cost‑aware builder: you treat latency and dollars as first‑class metrics and design for graceful degradation. 

• Vendor‑agnostic thinker: choose the right model/provider per use case; build for portability and resilience.