ML Engineer
LiteLLMSan FranciscoOn-Site
Needs a free Superjobs account. You'll finish on LiteLLM's Ashby page.
Skill score
Summary
The ML Engineer works directly with the CEO and CTO to unify LLM API calls behind the OpenAI and Anthropic specs, writing request transformations to provider formats and building provider-agnostic features such as session management and MCP auth flows. It suits a backend engineer with production experience who enjoys open source, talking to users, and shipping quickly in a small team.
- Function
- Data Science
- Estimated salary
- Est. $94k–141k/yr
- Estimated for a mid-level role, ~1 yr experience, United States. Not published by the employer.
- Work mode and location
- On-Site, San Francisco
- Experience
- 1–2 yrs
- Employment type
- Full-time
Job description
Roles and responsibilities
As the ML Engineer, you'll be responsible for ensuring LiteLLM unifies the format for calling LLM APIs in the broader OpenAI + Anthropic spec. This involves writing transformations to convert API requests from OpenAI/Anthropic spec to various LLM provider formats, building provider-agnostic unification functionality (e.g. session management across non-openai models for /v1/responses API, etc.). You'll work directly with the CEO and CTO on critical projects including:
- System design for supporting provider level features at the gateway level (skills, compaction, batches, etc.)
- Thinking about the developer experience - to support millions of users who leverage your work via LiteLLM's Python SDK
- Building across LLM's, MCP's, and Agents by maintaining an excellent LLM interoperability layer, supporting a wide range of MCP Auth flows and enabling various Agent use-cases
Skills required
Top skills
- Python
- LLM APIs
- FastAPI
- OpenAI API
All skills (4)
- Backend development
- Redis
- Postgres
- MCP
Qualifications
Skills: Python, LLM APIs, FastAPI
- 1-2 years of backend/full-stack experience with production systems
- Passion for open source and user engagement
- Experience working with the OpenAI api (understand the difference between /chat/completions and /responses, and can speak to API-specific nuances)
- Strong work ethic and ability to thrive in small teams
- Eagerness to talk to users and help solve real problems
Other details
The tech stack includes Python, FastAPI, Redis, Postgres.
Company info
About LiteLLM
LiteLLM is the world's most widely adopted AI Gateway. We provide a unified API for 100+ LLM providers along with routing, authentication, budgets, observability, and governance for production AI systems. Thousands of companies rely on LiteLLM to power AI in production.