ML Engineer

The role

You will make LLM API calls follow one shared format across providers, writing conversions from OpenAI and Anthropic formats to other provider formats. You will also work on system design and developer experience for the LiteLLM Python SDK, working directly with the CEO and CTO.

What you will do

• Write transformations that convert OpenAI and Anthropic API requests to various LLM provider formats
• Build provider-agnostic functionality, such as session management across non-OpenAI models for the /v1/responses API
• Design how provider-level features such as skills, compaction and batches are supported at the gateway level
• Improve the developer experience for millions of users of the LiteLLM Python SDK
• Maintain an LLM interoperability layer across LLMs, MCP and agents, including MCP auth flows
• Work directly with the CEO and CTO on critical projects

Required qualifications

• 1-2 years of backend or full-stack experience with production systems
• Passion for open source and user engagement
• Experience with the OpenAI API, including the difference between /chat/completions and /responses
• Strong work ethic and ability to thrive in small teams
• Eagerness to talk to users and help solve real problems
• Skills: Python, LLM APIs, FastAPI

Benefits

• Competitive salary
• Equity
• Health, dental and vision benefits
• Work directly with the founders every day
• Own meaningful product decisions
• See your work in production immediately

About the company

LiteLLM provides a unified API for 100+ LLM providers, along with routing, authentication, budgets, observability and governance for production AI systems. The posting says it is trusted by companies such as Adobe, Netflix and NASA.