Senior Backend Engineer, AI Platform & LLM Infra (Remote)

Azx; Seattle (WA); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Health insurance

Equity

Flexible paid time off

Bonus eligibility

Fully remote culture

Job summary

AZX is accelerating AI transformation with a focus on climate and sustainability. As a Backend Engineer, you will own LLM gateway infrastructure, retrieval services, and an async execution framework across hosted and self-hosted models.

You will work with Python-based tech stack (FastAPI, Pydantic, asyncpg, PostgreSQL) and collaborate with engineers delivering enterprise-grade AI solutions. This role offers a fully remote culture with a Seattle cluster and occasional travel for interviews and

Qualifications

• 5+ years of production-grade async Python experience with cancellation scopes and streaming lifecycle.
• Deep PostgreSQL infrastructure knowledge, MVCC, advisory locks.
• Experience shipping APIs used by other engineers with proper versioning and docs.
• Expertise in LLM gateway or retrieval engineering with credibility in the other area.
• Cost accounting mindset; shipped a gate or harness that caught a regression.
• Production depth in modern stack and ability to ramp on unfamiliar tools.
• Familiarity with Python 3.12+ stack: FastAPI/Starlette, Pydantic v2, asyncpg/SQLAlchemy, Postgres (pgvector), Redis/Dragonfly with Lua.
• Experience in energy, real estate, utilities, climate or related fields is a plus.
• Startup and enterprise experience is a plus.

Responsibilities

• Own the LLM gateway: routing, metering, budgets, guardrail composition, and provider/backend adapters across hosted and self-hosted models.
• Manage retrieval and knowledge service: connectors, chunking, hybrid search and reranking, grounded answers, MCP surface.
• Build the eval harness that turns retrieval tuning into evidence with confidence intervals and per-segment breakdowns.
• Own the async framework and its public API, rating limits, and admin tooling for durable execution of agent runs.
• Design authorization across the surface: token hierarchies and per-tenant isolation with regression testing.
• Define done criteria for shipped features: evals, traces, cost accounting, and dashboards.

Skills

Async Python

API design for engineers

Distributed systems

OpenTelemetry familiarity

Tools

PostgreSQL

Redis

SQLAlchemy

FastAPI

Lua

OpenTelemetry

Job description

AZX is accelerating AI transformation with a focus on climate and sustainability. As a Backend Engineer, you will own LLM gateway infrastructure, retrieval services, and an async execution framework across hosted and self-hosted models.

You will work with Python-based tech stack (FastAPI, Pydantic, asyncpg, PostgreSQL) and collaborate with engineers delivering enterprise-grade AI solutions. This role offers a fully remote culture with a Seattle cluster and occasional travel for interviews and