Senior Developer Engineer

OmniNode is building an AI governance infrastructure. It lets AI coding agents like Claude Code hand work off to the right model for the job. Routine tasks go to cheaper or local models, a quality gate checks every answer, and developers see exactly which model answered, what it cost, and why it was routed there. Our MVP is in the hands of our first testers now. We’re a small team building infrastructure that has to be correct, observable and fast.

The role

You’ll be one of the senior engineers shaping how OmniNode works: the delegation pipeline, routing and escalation logic, the event backbone, and the multi-tenant cloud runtime. You’ll work directly with our technical co-founder and CEO, own large parts of the system end to end, and set the engineering bar as the team grows.

What you’ll do

• Own core parts of the delegation pipeline: routing decisions, provider calls, quality gates, escalation, and run receipts
• Make delegation work in a correct and efficient manner before it’s clever.
• Build the multi-tenant runtime: tenant isolation, row-level security, credentials, and per-tenant event streams
• Integrate and benchmark model providers (OpenAI, Gemini, OpenRouter, local models via Ollama) and keep cost and token data accurate
• UI support and iterating.
• Harden the developer experience: the onex CLI, one-command onboarding, and the local dashboard
• Review code, mentor engineers and contractors, and help set architecture direction

What you bring

• 6+ years building production backend or distributed systems, with real ownership of systems people depend on
• Strong Python. Comfort reading and shipping in a multi-repo codebase.
• Experience with event-driven architecture (Kafka, Redpanda or similar), including delivery guarantees, idempotency and replay
• Production experience with Postgres, including schema migrations and multi-tenant data isolation
• Experience shipping on AWS with containers (Docker), CI/CD, and infrastructure you can reason about
• Hands-on experience building with LLM APIs. You know where they fail: rate limits, timeouts, token accounting, nondeterminism.
• You use AI coding agents in your own daily work and have opinions about where they waste money
• You write clearly, in PRs, design docs and Slack, not just AI slop with zero review or guidance

Bonus

• You’ve built LLM routing, evaluation or observability tooling
• Experience running local or open-weight models
• Open source contributions or maintainer experience
• Early-stage startup experience where you shipped across the whole stack

How to apply

Send:

• Your GitHub handle or links to work you’ve shipped
• A few sentences on the hardest correctness or reliability bug you’ve owned, and how you fixed it

Sign up to take a look at our product and Git repos https://omninode.ai/signup

Pay: $75,000.00 - $100,000.00 per year

Work Location: Remote