Senior Backend Engineer — Remote, Equity & Impact in AI

AZX; United States; Remote; USD 140,000 - 230,000; Full time

Benefits offered by this job

Health insurance

Equity

Flexible paid time off

Bonus eligibility

Job summary

AZX is hiring a Backend Engineer to build the services our AI products run on, with a focus on the LLM gateway and hosted/self-hosted models. You will ship the systems that monitor usage, budgets, and guardrails, collaborating with client‑facing engineers to deliver reliable outcomes.

You should have extensive Python async experience, strong PostgreSQL knowledge, and a track record shipping API surfaces. This role is fully remote with occasional travel to Seattle for interviews and summits.

Qualifications

• 5+ years of deep, production async Python — cancellation scopes, streaming lifecycle, and connection pooling.
• Postgres as infrastructure — MVCC, advisory locks, vacuum; Redis/Dragonfly used appropriately; real distributed‑systems experience.
• Experience shipping API surfaces with versioning, idempotency, error vocabularies, migration discipline, and documentation to match.
• Depth in at least one LL M gateway concern (routing, metering, guardrails) or retrieval engineering (hybrid search, reranking, eval methodology), with credibility on the other.
• A cost accounting and evals first mindset — you’ve shipped a gate or harness that caught a real regression.
• Production depth in some modern stack, and the aptitude to ramp quickly on unfamiliar tools.
• Familiarity with Python 3.12+ (async, type‑strict, FastAPI/Starlette, Pydantic v2), asyncpg/SQLAlchemy, Postgres (incl. pgvector), Redis/Dragonfly with Lua.
• Exposure to OpenTelemetry, SSE/streaming lifecycles, OpenAI/Anthropic provider APIs, job frameworks (Celery/Dramatiq/Prefect), rate‑limit algorithms, integer‑cents money handling.
• Past work in energy, real estate, utilities, climate or related fields is a plus.
• Experience in both startup and enterprise environments is a plus.

Responsibilities

• Own the LLM gateway: routing, metering, budgets, guardrail composition, and provider/backend adapters across hosted and self-hosted models.
• Manage the retrieval and knowledge service: connectors, chunking, hybrid search and reranking, grounded answers, and the MCP surface.
• Build the eval harness that turns retrieval tuning from judgment into evidence, with confidence intervals and per‑segment breakdowns.
• Own the async framework — its public API, rate‑limit algorithms, and admin tooling — and lead its evolution into durable execution for agent runs.
• Design authorization across the whole surface: token hierarchies, capability grammars, and per‑tenant isolation tested as a regression, not asserted in a doc.
• Own your own definition of done on everything you ship: evals, traces, cost accounting, and the dashboard that would wake you up.

Skills

Async Python

Distributed systems

API design

Cost accounting mindset

OpenTelemetry

OpenAI/Anthropic APIs

Research on LL gateway

Rag/ eval methodology

Power of Python stack

Tools

FastAPI/Starlette

Pydantic v2

asyncpg/SQLAlchemy

PostgreSQL with pgvector

Redis/Dragonfly with Lua

Lua scripting

Celery/Dramatiq/Prefect

OpenTelemetry

Job description

AZX is hiring a Backend Engineer to build the services our AI products run on, with a focus on the LLM gateway and hosted/self-hosted models. You will ship the systems that monitor usage, budgets, and guardrails, collaborating with client‑facing engineers to deliver reliable outcomes.

You should have extensive Python async experience, strong PostgreSQL knowledge, and a track record shipping API surfaces. This role is fully remote with occasional travel to Seattle for interviews and summits.