Why Cast AI?

Cast AI is an automation platform that operates cloud-native and AI infrastructure at scale. By embedding autonomous decision-making directly into Kubernetes and cloud environments, Cast AI continuously optimizes performance, reliability, and efficiency in production.
The old way doesn't work. As Kubernetes and AI environments grow, manual decisions don’t. Cast AI replaces tickets, alerts, and manual tuning with continuous automation that adapts infrastructure as conditions change. Efficiency and cost savings follow naturally from that automation.
Over 2,100 companies already rely on Cast AI, including Akamai, BMW, Cisco, FICO, HuggingFace, NielsenIQ, Swisscom, and TGS.

Global team, diverse perspectives

We're headquartered in Miami, but our impact is international. We take a global and intentional approach to diversity. Today, Cast AI operates across 34 countries spanning Europe, North America, Latin America, and APAC, bringing a wide range of perspectives into how we build and lead.

Unicorn momentum

In January 2026, we achieved unicorn status with a strategic investment from Pacific Alliance Ventures, the corporate venture arm of Shinsegae Group (a $50+ billion Korean conglomerate). Our valuation now exceeds $1 billion, and we're just getting started.

Join us as we build the future of autonomous infrastructure.

About the role

Throughput. Latency. KV cache utilization.

Move those three numbers in the right direction, and two things happen: customers get faster, cheaper inference, and our margins improve. That's the entire thesis of this role. Every kernel you tune, every quantization scheme you ship, every scheduler tweak you land shows up directly in a customer's p99 and on our P&L.
This is a high-impact seat. It is also a high-autonomy seat as you'll be given the room to lead the technical direction of inference optimization at Kimchi, not execute someone else's roadmap.

The problem: running LLMs in production is a moving target. The "right" model and serving configuration for a workload depend on traffic shape, sequence-length distribution, batch dynamics, GPU SKU, memory bandwidth, quantization tolerance, and a dozen other variables that shift week to week. Most teams pick a model once, over-provision GPUs, and absorb the cost. Kimchi is the system that makes that decision automatically - continuously matching workloads to the most cost-efficient, best-performing LLM and serving configuration on a customer's infrastructure. We're building the optimization layer between the model and the hardware, and we need engineers who understand both sides deeply.

Stack

Python; vLLM; SGLang; TensorRT-LLM; PyTorch; CUDA-adjacent tooling; Kubernetes; gRP; ClickHouse; PostgreSQL; GCP Pub/Sub; AWS / GCP / Azure; GitLab CI; ArgoCD; Prometheus; Grafana; Loki; Tempo.

Requirements:

• 5+ years building real ML systems, with a portfolio that shows depth in inference or training infrastructure (not just model training notebooks).
• Strong Python - production services, not scripts.
• Hands-on experience with at least one of vLLM, SGLang, or TensorRT-LLM, and a working mental model of why an inference engine performs the way it does on a given GPU.
• Fluency with quantization tradeoffs - you've measured quality regressions, not just compression ratios.
• Comfort with distributed systems: collective communication, sharding strategies, and the practical failure modes of multi-GPU and multi-node setups.
• A bias toward measurement. You instrument before you optimize, and you can tell the difference between a real win and a benchmark artifact.
• Self-direction. This role comes with a wide mandate; you should be excited by that, not unsettled by it.

Responsibilities:

• Push throughput. Continuous batching, speculative decoding, chunked prefill, kernel-level tuning across vLLM, SGLang, and TensorRT-LLM. Find the ceiling on each GPU SKU, then raise it.
• Cut latency. Attack TTFT and TPOT separately. Profile, identify the actual bottleneck (compute, memory bandwidth, scheduling, networking), and fix it - not the bottleneck you assumed.
• Get more out of the KV cache. Paged attention, prefix caching, eviction policies, cache reuse across requests, quantized KV. This is where a lot of the unrealized throughput lives, and it's an area you'll own.
• Quantize without regressing quality. INT8, INT4, FP8 across weights, activations, and KV. Empirical work: measure quality on real workloads, not just perplexity benchmarks.
• Shrink cold starts and memory footprint. Faster init, smarter weight loading, tighter memory accounting - the difference between a model that scales and one that doesn't.
• Scale across nodes. Distributed inference topologies, network-aware placement, checkpointing strategies that don't bottleneck on storage or interconnect.
• Set the technical direction. Decide what we benchmark, what we adopt, and what we build ourselves. Bring the team along with strong writeups and reproducible experiments.

What’s in it for you?

• Competitive salary (depending on the level of experience).
• Enjoy a flexible, remote-first global environment.
• Collaborate with a global team of cloud experts and innovators, passionate about pushing the boundaries of Kubernetes technology
• Equity options.
• Get quick feedback with a fast-paced workflow. Most feature projects are completed in 1 to 4 weeks.
• Spend 10% of your work time on personal projects or self-improvement. 
• Learning budget for professional and personal development - including access to international conferences and courses that elevate your skills.
• Annual hackathon to spark new ideas and strengthen team bonds.
• Team-building budget and company events to connect with your colleagues.
• Equipment budget to ensure you have everything you need.
• Extra days off to help maintain a healthy work-life balance.

Hiring process

• Screening call with Recruiter
• Hiring Manager interview
• Technical interview (system design)
• Live coding
• Culture Check interview with an executive

As part of our standard hiring process, we would like to inform you that a background check may be conducted at the final stage of recruitment through our third-party provider, Checkr.
Please note that Cast AI does not provide any form of visa sponsorship/work permit.

#LI-Remote

The Team:

You’ll join the Value Engineering team, a highly technical, strategic, customer-facing group that sits at the intersection of pre-sales, analytics, and transformation consulting. Value Engineers at Celonis are hands-on practitioners. They combine strong technical capability with consulting and stakeholder skills to guide customers through the full value journey — from first demo to long-term adoption and expansion.

The Role:

As an Applied AI Engineer (Pre-Sales) you are pushing the envelope in solving business-critical problems for our customers. You will be working with our most strategic customers, understanding their objectives and key challenges, and building Celonis solutions using the world’s leading Process Intelligence (PI) platform in combination with the largest AI and ML technology partners, such as Microsoft, OpenAI and Databricks. With Celonis’ Process Intelligence (PI) platform we feed operational context to AI so it understands our customers’ business and enables them to industrialize AI unlocking real ROI on AI deployments and at scale. There is no AI without PI. You will prototype these solutions, demonstrate their value to Executives and ensure successful implementation, adoption and value realization in order to increase the footprint of Celonis at those customers.

The work you’ll do:

• AI Discovery & Solutioning: Understand customers AI strategy and business critical challenges. As Celonis product & domain expert, find the best problem-solution fit and translate customer requirements into innovative solutions that move the needle
• Hackathons & Prototyping: Think out of the box, have a „can-do“ attitude and don’t shy away from complex problems. Leverage cutting edge AI technologies to rapidly build creative prototypes in customer hackathons solving business critical problems
• Agentic Process Transformation: Support our customers in achieving real ROI out of AI deployments at scale enabling a fundamental shift in business operations from traditional, rule-based automation to the use of autonomous AI agents empowered by our Celonis Process Intelligence Platform
• Proof projects: End-to-end execution of business-critical Proof-of-Value projects, incl. architecture and deliver secure, scalable LLM/agent systems with RAG, tools, and guardrails; integrating with enterprise data, identity, and compliance frameworks.
• Ensure Successful Project Outcome: Applied AI Engineers stay involved with projects until agreed value & adoption thresholds are reached
• Specialize in Domains or Industries: To scale knowledge across the organization Applied AI Engineers specialize in domains (e.g. supply chain) and industries

The qualifications you need:

•  3+ years of experience leading technical pre-sales, including defining AI roadmaps, building compelling ROI/TCO business cases and prototyping of machine learning and generative AI solutions.
• Understanding of generative AI techniques like RAG, few shot learning, prompt engineering, multi-agent orchestration, multimodal understanding, or fine-tuning that are used to build high-impact use cases like intelligent chatbots and automated text processors.
• Understanding of business processes across sectors (such as Supply Chain or Finance) with the ability to translate high-level business needs into specific AI use cases.
• Good knowledge of Python and common ML libraries (such as LangChain, pandas, pydantic, sklearn, PyTorch) as well as data engineering tools and technologies.
• Strong presentation skills to both internal and external stakeholders (including executives), whether whiteboarding sessions or formal readouts and demos.
• Bachelor’s Degree required, Masters Degree in computer science, physics, engineering, mathematics or related fields, or equivalent work experience preferred.
• Hybrid working environment - 3 days per week at our central Milan offices.  

Nice to have (big plus):

• Hands-on experience building agentic systems using LLM orchestration, RAG, function calling, and prompt engineering, while ensuring safety through rigorous evaluations and guardrails.
• Working knowledge of tools in the LLM ecosystem such as LangChain, LlamaIndex, or other OSS packages.
• Experience in deploying and monitoring models at scale across major cloud platforms (AWS Bedrock, Azure AI, GCP Vertex)