1 month ago
Base Salary
$140k - $230k/yr
Responsibilities
- Own the LLM gateway, including routing, metering, budgets, guardrails, and provider or backend adapters.
- Manage retrieval and knowledge services covering connectors, chunking, hybrid search, reranking, grounded answers, and the MCP surface.
- Build evaluation harnesses with confidence intervals and per-segment analysis for retrieval tuning.
- Own and evolve the asynchronous framework, public API, rate limiting, administration tools, and durable execution for agent runs.
- Design authorization with token hierarchies, capability grammars, and tested per-tenant isolation.
- Define completion criteria and ship evaluations, traces, cost accounting, and operational dashboards with each feature.
Requirements
- At least 5 years of deep production experience with asynchronous Python, including cancellation scopes, streaming lifecycles, and connection pooling.
- Strong Postgres infrastructure knowledge, including MVCC, advisory locks, vacuum discipline, and distributed-systems experience; experience with Redis or Dragonfly is expected.
- Experience shipping versioned, idempotent API surfaces for other engineers, including error vocabularies, migrations, and documentation.
- Depth in either LLM gateway engineering or retrieval engineering, with credible experience in the other area.
- Experience shipping evaluation gates or harnesses that identify real regressions, ideally including self-created regressions.
- Production experience with a modern technology stack and the ability to learn unfamiliar tools quickly.
- Familiarity with Python 3.12+, async programming, type-strict development, FastAPI, Starlette, Pydantic v2, asyncpg, SQLAlchemy, Postgres, pgvector, Redis or Dragonfly, and Lua.
- Exposure to OpenTelemetry and GenAI conventions, SSE and streaming lifecycles, OpenAI and Anthropic provider APIs, job frameworks such as Celery, Dramatiq, or Prefect, rate-limit algorithms, and integer-cents money handling.
- Experience in energy, real estate, utilities, climate, or related fields is preferred.
- Experience in both startup and enterprise environments is preferred.
- Must be authorized to work full-time in the United States; AZX cannot sponsor or transfer employment visas.
Benefits
- Competitive early-stage startup compensation based on capabilities, experience, and location.
- Bonus eligibility.
- Health insurance with meaningful dependent coverage.
- Flexible paid time off.
- Equity.
- Fully remote culture with a cluster of teammates in Seattle.
- Must travel to the Seattle area for the final interview and twice yearly for company summits.
Tech Stack
Categories
About AZX
Tech transformation, societal shifts and environmental disruption put enormous pressure on critical industries like energy, infrastructure, real estate and others to adapt, pursue new growth opportunities and optimize operations. AZX was created to meet these challenges head-on. We deliver AI transformation for critical industries providing strategy, execution and acceleration solutions. We prioritize code over powerpoint, applying start-up principles to challenge conventional thinking and develop strategic AI technology and business solutions that can be implemented quickly. We are mission-driven and client-centric, solving hard problems and building value for people, organizations and the planet. We are AZX.