About the Team At Business Technology, we use Appian to run Appian. We are launching our first internal AI team to build the foundation for how our global company works. This team won't just use AI, they will build the brain of the enterprise, spanning everything from predictive intelligence in our data warehouse to the GenAI infrastructure that powers our internal autonomous agents.

We are hiring a founding group of engineers to kickstart this mission. As an AI Engineer on this team, you won’t be maintaining legacy systems; you’ll be building from the ground up. You will own the full spectrum of AI: crafting predictive ML models to find insights in our data warehouse and architecting GenAI systems that allow any employee to interact with enterprise knowledge through intelligent agents.

If you want to be part of the original team that defines internal AI for a leading automation company, this is your moment.

PLEASE NOTE: This is a midlevel role and is aimed at people with 3+ years experience

What you’ll do:

• Build the AI Platform: Design, deploy, and scale GenAI infrastructure on GCP Vertex AI (preferred) or AWS Bedrock.
• Build & Operate MCP Servers: Develop and maintain Model Context Protocol (MCP) servers that expose enterprise systems (databases, APIs, internal tools) as structured, AI-consumable capabilities.
• Design the Tool Layer: Build the tool registry and invocation framework that allows agents to interact with internal systems safely and reliably including schema design, access controls, and error handling.
• Engineer Agent-to-Agent Infrastructure: Architect the communication and coordination layer that allows specialized agents to delegate tasks, share context, and compose into larger autonomous workflows.
• Own the Retrieval Layer: Architect and operate RAG systems, including vector stores, embedding pipelines, chunking strategies, and retrieval evaluation frameworks.
• Establish AI Reliability: Instrument AI systems with logging, tracing, latency monitoring, and evaluation hooks so agents can be trusted, debugged, and improved in production.

Required Qualifications:

• AI Infrastructure Experience: Professional experience building and deploying production-grade GenAI systems on GCP Vertex AI or AWS Bedrock including LLM APIs, agent frameworks, and RAG pipelines.
• Python Mastery: Deep proficiency in Python and common AI/ML libraries (e.g., LangChain, LlamaIndex, OpenAI SDK, Google Cloud AI SDK).
• Agentic Systems: Hands-on experience building multi-step, tool-calling AI agents that operate reliably in production including tool schema design, structured outputs, and failure handling.
• MCP or Tool Protocol Experience: Familiarity with Model Context Protocol (MCP) or equivalent patterns for exposing enterprise resources to AI systems as callable, permissioned tools.
• Vector & Retrieval Systems: Experience with vector databases (Pinecone, pgvector, or similar) and embedding-based retrieval at scale.
• Technical Foundation: B.S. in Computer Science, Engineering, or a related technical field.
• The Pioneer Mindset: A self-starter who is excited to be part of a "first-of-its-kind" team and thrives in environments where you are building the playbook.

Preferred Qualifications:

• Multi-Agent Architectures: Experience designing orchestrator/subagent patterns, agent handoff protocols, or systems where multiple AI models coordinate to complete complex tasks (e.g., using frameworks like LangGraph, CrewAI, or AutoGen).
• AI Observability: Experience with LLM evaluation frameworks, prompt regression testing, or agent trace monitoring (e.g. custom eval pipelines).
• Data Warehouse Integration: Familiarity with SQL and pulling data from Snowflake or BigQuery to ground AI agents in live business context.
• Appian Exposure: Experience with the Appian platform or interest in integrating AI agents into low-code automation workflows.
• Predictive ML (Nice to Have): Some familiarity with ML fundamentals is a plus, but not a focus of this role.

This role is based at our Chennai office in Brigade World Trade Center Chennai. Appian was built on a culture of in-person collaboration, which we believe is a key driver of our mission to be the best. Employees hired for this position are expected to be in the office 5 days a week to foster that culture and ensure we continue to thrive through shared ideas and teamwork. We believe being in the office provides more opportunities to come together and celebrate working with the exceptional people across Appian.  

Role Overview

We are seeking a Principal Applied Scientist to be the highest-level AI technical authority on the team. This role is above the Applied Scientist level — you set the AI research and engineering direction, own the agentic system architecture, define the eval framework standards, and operate as the primary interface to the external AI research community and internal platform AI leadership. You will combine deep research rigor with relentless production focus: every AI capability you design ships, gets measured, and improves based on evidence.

You are the person who answers: "Is this AI approach the right one, and how do we know when it's working"

Key Responsibilities

• Own the agentic system architecture: define the multi-agent coordination patterns, MCP tool taxonomy, intent-to-skill routing logic, policy enforcement design, and memory management strategy across all AI workflows on the platform.
• Lead the AI evaluation framework: design the golden dataset structure, define eval metrics (RAG retrieval quality, scoring accuracy, LLM response correctness, agentic workflow success rate), and own the CI/CD AI eval pipeline that gates every AI capability release.
• Drive the RAG architecture strategy: chunking strategies for MongoDB and Elasticsearch-indexed documents, embedding model selection and fine-tuning, retrieval reranking design, and hallucination mitigation patterns.
• Own the LLM integration architecture: prompt engineering standards, LLM gateway usage policies, context window management, streaming response patterns, and model version governance.
• Lead applied research initiatives: identify novel techniques (RLHF, Constitutional AI, multi-modal, sparse retrieval) that are practically applicable to automotive retail intelligence use cases and prototype them rigorously in Python.
• Define the hexagonal AI adapter contract standard: the formal interface specification between Python AI services and Java domain cores — ensuring AI infrastructure remains swappable without domain logic changes.
• Act as primary technical interface to platform AI leadership (LLM Gateway, ML Platform, Agentic Engine) — influencing platform roadmap based on teams practical requirements.
• Mentor the Applied Scientist and ML Architect; conduct technical reviews of AI system designs, eval frameworks, and research approaches.
• Publish, present, or contribute to open-source where appropriate — representing Tekion's AI engineering excellence externally.

Skills & Qualifications

• 10+ years of applied AI/ML experience with at least 3 years at Staff or Principal level — a track record of shipping AI systems that measurably changed business outcomes.
• Deep expertise across: LLM fine-tuning and alignment, RAG system design (chunking, embedding, retrieval, reranking), agentic frameworks (LangGraph, CrewAI, AutoGen), and MCP tool design.
• Python mastery: PyTorch, Hugging Face Transformers, LangChain/LangGraph, scikit-learn, and production ML serving tooling.
• Strong understanding of distributed AI systems: Elasticsearch-backed vector search, Redis/Aerospike serving, Cosmos DB for AI event logging, and Kafka-based feature pipelines.
• Proven ability to design formal eval frameworks for AI systems — not just accuracy metrics but business aligned quality gates.
• Experience defining and enforcing hexagonal adapter contracts between AI services and domain service layers in production systems.
• Track record of communicating complex AI system design to non-technical stakeholders, influencing product roadmaps, and driving cross-team alignment. 

Good to Have

• Publications or significant open-source contributions in NLP, information retrieval, or agentic systems.
• Experience with Constitutional AI, RLAIF, or preference optimization techniques (DPO, PPO).
• Familiarity with multi-modal AI and its application to automotive retail data (images, documents, tabular data fusion).
• Prior experience in a product-focused AI role at a SaaS or platform company — not purely research. 

Perks & Benefits

• Competitive compensation and generous stock options.
• Medical insurance coverage.
• Work with some of the brightest minds from Silicon Valley's most dominant and successful companies.