Fuel Cycle is building production AI agents, and this early-career Associate AI Engineer role places you in the middle of real systems work alongside senior engineers. The position is fully in-office in Los Angeles, CA, with a mentorship model that relies on pair programming, in-person code review, and an available mentor a few desks away. You will work primarily with Python and FastAPI, and contribute to agent delivery on AWS Bedrock / AgentCore.
What you’ll do
- Design, build, and continuously improve AI agents, including how tool-calling loops, model configuration, and multi-step workflows are structured using Strands Agents and AWS Bedrock
- Build and integrate Model Context Protocol (MCP) tools and servers, learning how tool names and descriptions influence LLM behavior
- Deploy and run agents on Bedrock AgentCore in collaboration with the platform team and your mentor
- Create RAG pipelines using pgvector or FAISS, selecting chunking, embedding, and retrieval approaches based on measured results
- Design, test, and iterate on prompts; evaluate answer quality, latency, and token cost, and apply production guardrails
- Evaluate models, tools, and approaches, recommending what to use with documented reasoning
- Ship features and bug fixes in FastAPI services, including REST and WebSocket APIs backed by PostgreSQL and Redis
- Contribute to background jobs and queue consumers so agent work runs outside the API request path
- Follow architectural standards, apply judgment within those standards, help keep design documentation current, and flag where standards should change
- Submit pull requests, respond to review feedback, and review teammates’ code as you grow
What you bring
- Strong Python fundamentals from coursework, internships, or work, including functions, classes, type hints, error handling, and testing basics
- Data structures and algorithms, with awareness of time and space complexity
- SQL fundamentals (joins, aggregations, indexes, schema design), with PostgreSQL exposure preferred
- REST and HTTP concepts and how an API is structured
- Git and pull-request workflow
- Clear communication, comfort asking questions, and a habit of learning new tools and seeking help when blocked
Helpful experience (preferred)
- An agent project built with Strands Agents, LangChain, OpenAI SDK, or a similar framework, including understanding how an LLM chooses and calls tools
- Hands-on MCP experience, building or using MCP tools and servers
- AWS Bedrock or Bedrock AgentCore experience (or AWS basics like S3 and SQS)
- RAG experience covering chunking, embeddings, and vector stores
- Prompt engineering experience: writing, testing, and iterating on prompts
- Experience with FastAPI (or similar frameworks like Flask or Django), and familiarity with SQLAlchemy or another ORM, plus willingness to learn async Python
Compensation & benefits
Salary: $90,000 - $110,000 per year. Final base salary is determined based on location, work experience, skills, knowledge, education, and certifications. The role is eligible for variable bonus, and may include an equity grant or equity purchase option.
- Medical, dental, and vision insurance plans
- 401(k) with Company Match
- Equity Purchase Option
- Flexible Work Schedule
- 15 vacation days and 7 sick days per year
- 12 company holidays
- 4 floating holidays/recharge days
- Paid Parental Leave
- Monthly Internet & Phone Stipend
- Wellness & Lifestyle Perks (Rightway, Headspace, Peloton)
- Weekly community lunches, refreshments, and snacks at our LA & NY headquarters
Equal opportunity
Fuel Cycle is committed to fostering an inclusive company culture and is an equal opportunity employer. Fuel Cycle stands against discrimination based on disability, sex, race, gender identity, sexual orientation, religion, national origin, age, veteran status, or any other protected status under the law, and fully complies with the Americans with Disabilities Act (ADA). If you require accommodations during any part of the application process, contact hr@fuelcycle.com.
