Flexcompute Inc. is looking for an AI/ML Engineer to build and scale our AI-powered simulation assistant. This role combines LLM orchestration with semantic search in a domain where precision and technical accuracy matter. You will own the full stack from embeddings pipelines to production inference, working closely with physicists and engineers to ground AI outputs in scientific correctness.
What You'll Do
- Design and maintain LLM-based agentic systems for physics simulation workflows
- Build semantic search and retrieval pipelines over technical documentation and simulation data
- Develop embedding pipelines: chunking strategies, vector stores, retrieval evaluation
- Deploy and operate containerized ML services on AWS (ECS, Lambda, S3)
- Optimize LLM inference costs, latency, and quality at scale
- Integrate AI capabilities into IDE extensions (VS Code, Cursor) via MCP
What We're Looking For
- M.Sc. or Ph.D. in Computer Science, Machine Learning, or related field (or equivalent industry experience)
- 2+ years building production AI/ML systems (not just prototypes)
- Hands-on experience with LLM APIs (OpenAI, Anthropic) and prompt engineering
- Strong understanding of embeddings and vector databases (Weaviate, Chroma, pgvector)
- Proficiency in Python; working knowledge of TypeScript
- Track record of shipping AI features to end users
Nice to Have
- Experience with agentic LLM frameworks (LangChain, LlamaIndex, Pydantic AI, DSPy)
- Experience building LLM evaluation pipelines
- Familiarity with MCP (Model Context Protocol) or similar agent-tool interfaces
- Background in scientific/technical domains (physics, engineering, simulation)
- Production AWS experience (EC2, ECS, Lambda)
- Experience with containerization (Docker) and observability tooling
- Knowledge of traditional ML beyond LLMs
Technical Stack
- Languages: Python, TypeScript
- Infrastructure: AWS (ECS, Lambda, S3, EC2), Docker
- AI/ML: LLM APIs (OpenAI, Anthropic), Vector databases (Weaviate, Chroma, pgvector)
- Frameworks: Agentic frameworks (LangChain, LlamaIndex, Pydantic AI, DSPy), MCP (Model Context Protocol)
Team & Environment
You will work closely with physicists and engineers in a team of friendly, thoughtful, and intelligent coworkers.
Benefits & Compensation
- Competitive compensation with equity
- Medical, dental, and vision health insurance
- 401(k) Contribution
- Gym allowance
- Friendly, thoughtful, and intelligent coworkers
Work Mode
This is a remote position.
Flexcompute is dedicated to providing equal employment opportunities. We firmly believe that talent from diverse backgrounds can bring our company a rich and varied perspective. We warmly welcome candidates from all backgrounds to join us.
