Backend Engineer (OpenAI API)

Rise Technical Recruitment Limited; San Francisco (CA); On-site; USD 200,000 - 250,000; Full time

Benefits offered by this job

Equity

Benefits

On-site

Job summary

Rise Technical Recruitment Limited is hiring a Backend Engineer to work on OpenAI API integrations in San Francisco, on-site.

You will write transformations between provider formats, build provider-agnostic unification, and shape the developer experience for millions of users via the Python SDK. This early engineering hire will report to the CEO and CTO and contribute directly to product decisions.

Qualifications

• 1+ years of backend or full-stack experience with production systems.
• Experience with the OpenAI API and understanding of /chat/completions vs /responses.
• Eager to talk to users and solve real problems.

Responsibilities

• Write transformations converting API requests between OpenAI/Anthropic specs and provider formats.
• Build provider-agnostic unification functionality, including session management across non-OpenAI models.
• Design systems supporting provider-level features at the gateway level (skills, compaction, batches).
• Support MCP Auth flows and enable various Agent use-cases.
• Shape developer experience for millions of users via the Python SDK.

Skills

Backend development

OpenAI API experience

Python

Team collaboration

Education

CS degree or equivalent

Tools

OpenAI API

Job description

Backend Engineer (OpenAI API)
$200,000 - $250,000 + Equity + Benefits
On-site in San Francisco, CA

Are you a backend engineer who takes pride in building clean, provider-agnostic systems at scale? Do you care deeply about developer experience, building interfaces that millions of users will interact with through a Python SDK, rather than just making something technically work?

This is an opportunity to join a fast-growing, profitable startup at the forefront of AI infrastructure, building the compliance and reliability layer that enterprise customers like Adobe, Netflix, and NASA depend on in production.

Backed by top-tier investors, the team has built the world's most widely used LLM Gateway, a unified platform that gives developers secure, scalable access to every major LLM provider. Now, they're building their second product, and looking for an AI Engineer to ensure the platform unifies the format for calling LLM APIs across the OpenAI and Anthropic spec.

As an early engineering hire, you'll work directly with the CEO and CTO on writing transformations that convert API requests across provider formats, building provider-agnostic unification functionality, and maintaining an excellent LLM interoperability layer across LLMs, MCPs, and Agents.

If you're looking for a role where your engineering work is used directly by thousands of engineering teams around the world, with real ownership over product decisions and not just implementation, this is an outstanding opportunity.

The Role

• Write transformations converting API requests from OpenAI/Anthropic spec to various LLM provider formats


• Build provider-agnostic unification functionality, including session management across non-OpenAI models


• Design systems supporting provider-level features at the gateway level (skills, compaction, batches)


• Support a wide range of MCP Auth flows and enable various Agent use-cases


• Shape developer experience for millions of users via the Python SDK

The Person

• 1+ years of backend or full-stack experience with production systems


• Experience working with the OpenAI API, understands the nuances between /chat/completions and /responses


• Eager to talk to users and help solve real problems


• CS degree or equivalent from a top 30 program in the US or Canada

We are an equal opportunities company and welcome applications from all suitable candidates.