ML Engineer: LLM Interop & AI Gateway (Equity)

LiteLLM; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

Competitive salary

Equity and benefits (health, dental, &

Vision benefits

Job summary

LiteLLM is building the next generation of AI infrastructure and is seeking an ML Engineer to unify LLM API calls across the OpenAI and Anthropic specs. You will transform API requests, create a provider-agnostic layer, and work directly with the CEO and CTO on critical projects that impact millions of users.

The role emphasizes system design, developer experience through the Python SDK, and interoperability across MCPs and Agents, enabling diverse use-cases and fast production delivery.

Qualifications

• 1-2 years of backend/full-stack experience with production systems.
• Passion for open source and user engagement.
• Experience working with the OpenAI API and understanding /chat/completions vs /responses.

Responsibilities

• System design for provider-level features at the gateway level (skills, compaction, batches).
• Enhance developer experience for LiteLLM’s Python SDK to support millions of users.
• Build across LLMs, MCPs, and Agents with an interoperable layer and varied Auth flows.

Skills

Python

LLM APIs

FastAPI

Job description

LiteLLM is building the next generation of AI infrastructure and is seeking an ML Engineer to unify LLM API calls across the OpenAI and Anthropic specs. You will transform API requests, create a provider-agnostic layer, and work directly with the CEO and CTO on critical projects that impact millions of users.

The role emphasizes system design, developer experience through the Python SDK, and interoperability across MCPs and Agents, enabling diverse use-cases and fast production delivery.