Backend Engineer

Provn; Seattle (WA); Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Remote work in US

Equity options

Health insurance

Flexible PTO

Job summary

AZX is hiring a Backend Engineer to design and optimize its AI Platform infrastructure. You will build and maintain an LLM gateway, retrieval and evaluation tooling, and an asynchronous execution framework with robust security and cost controls.

This is a full-time, remote role within the United States, collaborating with client-facing engineers to deliver impactful solutions. You will work with modern stacks including Python 3.12+, FastAPI, SQLAlchemy, Postgres with pgvector, Redis, and Lua

Qualifications

• 5+ years of production experience with asynchronous Python.
• Strong PostgreSQL background, MVCC, vacuum, and performance tuning.
• Experience with Redis and optional Dragonfly for storage layers.
• Proven API surface shipping with versioning and error handling.
• Familiarity with OpenTelemetry and tracing in GenAI contexts.
• Proficiency with FastAPI/Starlette, SQLAlchemy, and pgvector.

Responsibilities

• Architect and maintain LLM gateway with routing, metering, and guardrails.
• Oversee retrieval service, connectors, hybrid search, and RAG eval.
• Design evaluation harness with confidence intervals and analyses.
• Advance asynchronous framework API, rate-limiting, and admin tools.
• Enforce authorization protocols and per-tenant isolation with tests.
• Own features end-to-end including tracing, costs, and dashboards.

Skills

Asynchronous Python

PostgreSQL

Redis

API design

OpenTelemetry

FastAPI

SQLAlchemy

Tools

PostgreSQL

Redis

Dragonfly

Lua

pgvector

OpenTelemetry

FastAPI

Job description

Backend Engineer - Summary

AZX, a pioneering public benefit corporation, is seeking a skilled Backend Engineer to contribute to the development and optimization of its AI Platform. This is a full-time, remote position within the U.S., offering the opportunity to work on leading-edge technology that enables critical industries to leverage artificial intelligence for sustainability, clean energy, decarbonization, and climate risk management. As a Backend Engineer, you will play a crucial role in designing and maintaining the infrastructure that powers advanced machine learning solutions, serving both internal and external stakeholders. Working closely with client-facing engineers, you will receive direct feedback and concrete requirements, ensuring your work has immediate impact and relevance. AZX’s mission-driven culture, focus on long-term success, and commitment to positive global impact make it an exceptional environment for professionals passionate about AI and societal change.

Duties & Responsibilities

• Architect, build, and maintain the LLM (Large Language Model) gateway, ensuring robust routing, metering, budget management, guardrail composition, and seamless integration with multiple AI models, both hosted and self-hosted.
• Oversee the retrieval and knowledge service, including development and optimization of connectors, data chunking, hybrid search and reranking algorithms, grounded answer generation, and the MCP (Model Control Panel) interface.
• Design and implement an evaluation harness that transforms retrieval tuning into a data-driven process, providing confidence intervals and detailed per-segment analysis.
• Lead the evolution of the asynchronous framework, enhancing its public API, rate-limit algorithms, and administrative tools, and guiding its transition into a durable execution system for agent operations.
• Establish and enforce authorization protocols across the platform, including token hierarchies, capability grammars, and per-tenant isolation, with comprehensive regression testing.
• Maintain full ownership over shipped features, including evaluation, tracing, cost accounting, and dashboard development, ensuring reliability and accountability.

Salary & Benefits

• Competitive early-stage startup compensation, including base salary, bonus eligibility, and equity options based on experience and capabilities.
• Comprehensive health insurance coverage, including meaningful support for dependents.
• Flexible paid time off to encourage work-life balance and employee well-being.
• Opportunity to work fully remotely, with occasional travel for company summits and a strong virtual team culture.
• Engagement with industry-leading clients driving AI transformation in real estate, energy, logistics, and utilities.

Qualifications & Requirements

• Minimum of 5 years of hands-on, production-level experience with asynchronous Python, including expertise in cancellation scopes, streaming lifecycles, and connection pooling.
• Proficiency in using Postgres as infrastructure, with an understanding of MVCC (Multi-Version Concurrency Control), advisory locks, and vacuum processes. Practical experience with Redis or Dragonfly is also required, applied judiciously as appropriate for system needs.
• Proven track record in shipping robust API surfaces for engineering teams, with skills in versioning, idempotency, error handling, migration discipline, and comprehensive documentation.
• Demonstrated depth in at least one of the following areas: LLM gateway operations (routing, metering, guardrails, provider failover) or retrieval engineering (hybrid search, reranking, evaluation methodologies, audit-ready RAG), and familiarity with the other domain.
• Mindset focused on cost accounting and evaluation, with experience deploying gates or harnesses that identify and correct regressions.
• Fluency in modern technology stacks, with the capacity to quickly learn and adapt to new tools.
• Practical familiarity with core technologies: Python 3.12+ (async, type-strict, FastAPI/Starlette, Pydantic v2), asyncpg/SQLAlchemy, Postgres (including pgvector), Redis/Dragonfly with Lua, and willingness to research and expand knowledge as necessary.
• Exposure to supporting technologies such as OpenTelemetry (including GenAI conventions), server-sent events/streaming lifecycles, OpenAI/Anthropic APIs, job frameworks (e.g., Celery, Dramatiq, Prefect), rate-limit algorithms (token bucket, GCRA), and financial transaction handling.
• Authorization to work in the U.S. on a full-time basis. Visa sponsorship is not available at this time.

Ideal Candidate Snapshot

• Experienced in backend engineering for AI or machine learning platforms, preferably with exposure to enterprise-scale systems.
• Possesses strong analytical and problem-solving abilities, with a meticulous approach to system design, evaluation, and monitoring.
• Comfortable collaborating in a fast-paced, feedback-driven environment, and able to work independently in a remote setting.
• Previous experience in sectors related to energy, real estate, utilities, or climate is a plus, as is familiarity with both startup and enterprise environments.
• Demonstrates a passion for AI, sustainability, and contributing to positive societal impact through technology.

Other Relevant Information

AZX is a public benefit corporation founded in 2024 and has maintained profitability from inception, ensuring stability and growth opportunities for team members.

The company culture is mission-driven, with a focus on making a meaningful difference in critical global challenges through AI innovation.

Full-time, remote work is supported, with company summits and team collaboration events held periodically.

AZX and its partners engage in a thorough and engaging hiring process, including skills challenges and video presentations to assess technical and communication strengths.

The company is committed to equal opportunity employment and building a diverse, inclusive team. All qualified applicants will receive consideration without regard to race, color, religion, sex, sexual orientation, gender identity or expression, national origin, age, disability, veteran status, or any other characteristic protected by law.

Join AZX and help shape the future of AI-powered innovation in critical industries.