AI Engineer

Recruiting From Scratch•San Francisco, CA

38d•Onsite

About The Position

We are representing an early-stage AI infrastructure company that is building one of the world's most widely adopted AI gateways. Their platform offers a unified interface across over 100 LLM providers, enabling engineering teams to standardize model access, routing, authentication, budgets, observability, and governance. This technology is currently utilized by thousands of engineering teams and trusted by prominent organizations such as Adobe, Netflix, and NASA. The company is now expanding its offerings beyond its core gateway product, continuing to develop foundational infrastructure for LLMs, MCP, and AI agents. This role presents an opportunity to join a small, highly technical team and collaborate directly with the founders on infrastructure that supports developers building production AI applications.

Requirements

1–2+ years of professional backend or full-stack engineering experience building production systems.
Strong Python experience.
Experience building APIs and backend services, ideally using technologies such as FastAPI.
Meaningful hands-on experience working with the OpenAI API.
Understands the differences between /chat/completions and /responses and can discuss API-specific behavior and implementation nuances.
Strong understanding of modern LLM APIs and how developers integrate models into production applications.
Comfortable learning the APIs and behavior of different model providers and translating between them.
Strong engineering fundamentals around API design, reliability, and production software.
Comfortable operating with significant ownership on a small engineering team.
Interested in speaking directly with users and solving real developer problems.
High level of curiosity and interest in the rapidly evolving AI infrastructure ecosystem.

Nice To Haves

Experience building LLM infrastructure, AI gateways, or developer tooling.
Experience working across multiple LLM providers rather than exclusively with a single model API.
Familiarity with Anthropic's API in addition to OpenAI.
Experience with MCP and emerging agent infrastructure.
Experience building or contributing to open-source software.
Experience maintaining SDKs, APIs, or developer-facing infrastructure with significant external usage.
Familiarity with Redis and PostgreSQL.
Experience thinking deeply about developer experience and API ergonomics.
Comfortable working directly with founders in a fast-moving early-stage environment.

Responsibilities

Build and maintain the interoperability layer that provides a unified interface across a large number of LLM APIs and providers.
Develop transformations between OpenAI and Anthropic API specifications and the native formats of other model providers.
Build provider-agnostic functionality across LLM APIs, including session management and /v1/responses functionality.
Design gateway-level systems supporting provider capabilities such as skills, compaction, batches, and other emerging model features.
Build developer infrastructure used by millions of users through the company's Python SDK.
Work across LLMs, MCP, and AI agents, helping create a consistent developer experience across rapidly evolving ecosystems.
Support a wide variety of MCP authentication flows and agent use cases.
Work directly with the CEO and CTO on architecture, product, and engineering decisions.
Engage directly with developers and customers to understand problems and translate feedback into product improvements.
Ship quickly and take meaningful ownership over both implementation and product decisions.