Senior Backend Engineer (AI Platform)
- Role
- Backend
- Experience
- Senior
- Employment
- Full-time
- Company size
- Startup
Open to US only. Set where you work from to check your eligibility.
No BS summary
Senior backend engineer to build LLM infrastructure and AI platform services using async Python. Requires 5+ years production async Python and strong Postgres experience; depth in LLM gateway or retrieval engineering. Applicants must be authorized to work in the United States (no visa sponsorship).
Core skills
Required skills
About AZX
Our mission is to accelerate positive impact in critical industries through AI transformation. We specialize in physics-informed ML and enterprise AI solutions that directly address climate and sustainability challenges.
We’re growing quickly and already work with category-leaders in real estate (CBRE), energy (LevelTen Energy), logistics (Flexe) and utilities.
We’re a public benefit corporation, founded in 2024, and have been profitable from inception.
We work on challenges in clean energy, decarbonization, climate risk, energy systems, and global economics. We’re building our company for long-term success and aim to create the ultimate place to work for those passionate about AI and making a positive impact.
About the Role
As a Backend Engineer you will build the services our products and client solutions run on. The center of gravity is LLM infrastructure: the layer that puts one governed front door over many models, hosted and self-hosted, and answers the questions enterprises actually ask — who used which model, for what, at what cost, under whose rules. The platform's first customers are our own client-facing engineers, the people delivering client outcomes with what you build, so requirements arrive concrete, feedback arrives same-day, and the people you support are in the same meeting.
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.
Core Qualifications:
- 5+ years of deep, production async Python — cancellation scopes, streaming lifecycle, and connection pooling
- Postgres as infrastructure — comfortable reasoning about MVCC, advisory locks, and vacuum discipline, with Redis/Dragonfly used (and not used) where it belongs; real distributed-systems experience, not just familiarity.
- Experience shipping API surfaces other engineers build on — versioning, idempotency, error vocabularies, migration discipline, and documentation to match.
- Depth in at least one of LLM gateway concern (routing, metering, guardrails, provider failover) or retrieval engineering (hybrid search, reranking, eval methodology, audit-ready RAG), with credibility on the other.
- A cost accounting and evals first mindset — you've shipped a gate or harness that caught a real regression, ideally one of your own.
- Production depth in some modern stack, and the aptitude to ramp quickly on unfamiliar tools
- Practical familiarity with our core stack — Python 3.12+ (async, type-strict, FastAPI/Starlette, Pydantic v2), asyncpg/SQLAlchemy, Postgres (incl. pgvector), and Redis/Dragonfly with Lua — with willingness to research into the rest.
- Exposure to the surrounding ecosystem: OpenTelemetry (incl. GenAI conventions), SSE/streaming lifecycles, OpenAI/Anthropic provider APIs, job frameworks (Celery/Dramatiq/Prefect-class), rate-limit algorithms (token bucket, GCRA), and 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
Why AZX!
- Be part of a fast-growing, profitable, mission-driven company with industry-leading clients tackling the massive opportunity of AI transformation in critical industries.
- Competitive early-stage startup compensation (based on capabilities, experience, and location)
- Bonus eligibility
- Health insurance with meaningful coverage for dependents
- Flexible paid time off
- Equity
- Fully remote culture with a cluster of teammates in Seattle
Additional Information:
- Must be willing to travel to Seattle area for final interview and travel 2x/year for company summits
- Applicants must be currently authorized to work in the United States on a full-time basis.
- We are unable to sponsor or take over sponsorship of employment visas at this time.
- Please only apply to a maximum of 2 roles at a time, any applicants who apply to more then 2 roles within a 6 month period will automatically be disqualified
Next Steps:
If this job sounds like a great fit but don’t check ALL of these qualification boxes, we’d still love to hear from you!
What you'll do
- 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 for retrieval tuning with confidence intervals and per-segment breakdowns.
- Own the async framework: public API, rate-limit algorithms, admin tooling, and evolve it into durable execution for agent runs.
- Design authorization across the platform: token hierarchies, capability grammars, and per-tenant isolation, with regression tests.
What they require
- 5+ years of deep, production async Python (cancellation scopes, streaming lifecycle, connection pooling).
- Postgres infrastructure experience: comfortable reasoning about MVCC, advisory locks, and vacuum discipline; Redis/Dragonfly used where appropriate.
- Depth in at least one of LLM gateway concerns (routing, metering, guardrails, provider failover) or retrieval engineering (hybrid search, reranking, eval methodology, audit-ready RAG).
- Must be currently authorized to work in the United States on a full-time basis; unable to sponsor or take over sponsorship of employment visas.
- Practical familiarity with core stack: Python 3.12+ (async, type-strict), FastAPI/Starlette, Pydantic v2, asyncpg/SQLAlchemy, Postgres (incl. pgvector), Redis/Dragonfly with Lua.
Benefits
- Equity
- Bonus eligibility
- Health insurance with meaningful coverage for dependents
- Flexible paid time off
- Fully remote culture with a cluster of teammates in Seattle
Our mission is to accelerate positive impact in critical industries through AI transformation. We’re growing quickly and already work with category-leaders in real estate (CBRE), energy (LevelTen Energy), logistics (Flexe), and utilities (Puget Sound Energy). AZX is a public benefit corporation founded in 2024. We were profitable through bootstrapped consulting for the first year. In early 2026, we raised $6M to scale our operations and technology. We work on challenges in clean energy, decarbonization, climate risk, energy systems, and global economics. We’re building our company for long-term success and aim to create the ultimate place to work for those passionate about AI and making a positive impact.