Full-Stack Engineer (Backend-Leaning) – AI Infrastructure

Full-Stack Engineer (Backend-Leaning) – AI Infrastructure

Location: San Francisco, CA (on-site, 5 days per week)

Salary: $130,000–$180,000 base + 0.25–1% equity

Working hours: Full-time, approximately 9:00 AM–9:00 PM, 5 days per week

Visa sponsorship: Possible

About the Company

Our client is a seed-stage AI infrastructure company with a team of fewer than ten people, building continuous-improvement systems for enterprise AI agents.

Its platform acts as a control plane for the knowledge powering production chatbots and AI agents, connecting real-world performance with the underlying knowledge those systems rely on. This enables businesses to evaluate agent performance, identify knowledge gaps, and continuously improve their AI applications.

Despite its small size, the company already has live deployments with Fortune 50 brands across media, telecommunications, and financial services. Its customers include support and IT teams operating in regulated industries, where reliability, observability, and data quality are critical.

About the Role

We're looking for a backend-leaning Full-Stack Engineer to help build and scale the infrastructure behind the company's AI agent evaluation and continuous-improvement platform.

Most of the technical challenges sit on the backend, spanning data modelling, queues, execution pipelines, enterprise integrations, observability, and distributed systems reliability. You'll also work across the full stack, taking features from initial design through deployment and ongoing improvement.

You'll join a highly technical, early-stage team where engineers have genuine ownership of architecture and product decisions. The role offers the opportunity to work on complex production systems, collaborate directly with enterprise customers when needed, and help shape a growing AI infrastructure product.

Key Responsibilities

• Build core backend systems: Develop and maintain the infrastructure powering agent evaluation and continuous improvement.
• Design data models: Structure and manage evaluation datasets, experiment runs, agent traces, knowledge versions, and findings.
• Own enterprise integrations: Build integrations end to end, including OAuth, webhooks, incremental synchronisation, backfills, rate limits, retries, and monitoring.
• Develop reliable workflows: Build and optimise queues, background workers, execution pipelines, and distributed workflows.
• Deliver full-stack features: Take product functionality from design and implementation through deployment, monitoring, and customer feedback.
• Improve observability and reliability: Ensure production systems are measurable, resilient, and straightforward to debug.
• Influence product and architecture: Contribute directly to technical strategy and product decisions in a small, fast-moving engineering team.

Requirements

• 3–6 years of experience building and operating production software.
• Strong backend engineering skills combined with the ability to deliver full-stack features.
• Production experience with TypeScript and Node.js or Bun.
• Strong PostgreSQL skills, including data modelling and query optimisation.
• Experience with Redis, job queues, background workers, or workflow orchestration systems.
• Experience building APIs, enterprise integrations, webhooks, and data pipelines for multi-tenant production software.
• Understanding of observability, distributed systems, and production debugging.
• Ability to take ownership of features and systems from design through deployment and ongoing operation.

Familiarity with AI agent evaluation, LLM observability, or machine learning infrastructure is a plus.

Ideal Background

The strongest candidates combine deep backend expertise with practical product engineering experience.

Particularly relevant experience includes:

• Building integration-heavy backend systems in multi-tenant SaaS environments.
• Working extensively with PostgreSQL alongside queues, background workers, or workflow systems.
• Owning complex enterprise integrations from initial implementation through production monitoring and maintenance.
• Developing observability tools or infrastructure for LLM-powered applications and AI agents.
• Working in a startup environment after gaining strong engineering experience at a technically demanding company.

We're looking for an engineer who takes ownership, thinks critically about architecture, and can independently solve complex production problems.

This is not a front-end-focused role. Candidates need substantial backend depth, hands-on experience with multi-tenant systems and integrations, and strong TypeScript/Node.js and SQL skills. Engineers who primarily execute predefined tickets without taking ownership of technical decisions are unlikely to be a fit.

Interview Process

1. Initial founder and technical screening.
2. Technical interview and architecture discussion.
3. Practical work trial or on-site assessment.
4. Offer.

Why Join?

• Build core AI infrastructure: Work on the systems that help enterprise AI agents continuously improve.
• Take real ownership: Influence architecture, product direction, and engineering decisions from an early stage.
• Solve challenging backend problems: Work with distributed workflows, complex integrations, observability, and production reliability.
• Work with major enterprise customers: Help support live deployments across regulated industries.
• Share in the upside: Receive equity in an ambitious, early-stage AI company.
• Join a small, technical team: Make a direct impact without the layers of bureaucracy found in larger organisations.

If you're a backend-focused engineer who enjoys building reliable production systems, owning complex integrations, and contributing across the stack, this is an opportunity to help shape the future of enterprise AI infrastructure.