Backend Engineer (Guardrails & Observability)

Backend Engineer – LLM Guardrails & Observability (AI DevTool Start-Up)

$120,000 – $160,000 + Equity + Benefits + PTO

On-site in San Francisco, CA

Are you a recent CS graduate who takes pride in building reliable, airtight backend systems? Do you care deeply about making sure nothing slips through the cracks, that errors are caught, logged, and surfaced rather than silently swallowed?

This is an opportunity to join a fast-growing, profitable startup at the forefront of AI infrastructure, building the compliance and reliability layer that enterprise customers like Adobe, Netflix, and NASA depend on in production.

Backed by top-tier investors, the team has built the world's most widely used LLM Gateway — a unified platform that gives developers secure, scalable access to every major LLM provider.

Now, they're looking for a Backend Engineer to own the guardrails and observability layer that keeps the platform trustworthy at scale.

As an early engineering hire, you'll take direct ownership of the systems that log, track, and surface everything happening inside the policy enforcement layer. You'll work across internal teams to eliminate silent failures, build out monitoring integrations, and ensure that every guardrail call leaves a clear, auditable paper trail.

If you're looking for a role where your attention to detail directly drives enterprise trust and platform reliability, whilst benefiting from strong equity in an already profitable company before they raise their Series A, this is an outstanding opportunity.

The Role:

• Own the logging and traceability of all guardrail and policy enforcement calls across the platform
• Identify and eliminate silent failures in guardrail creation, registration, and application
• Build and maintain integrations with observability tools including Datadog, Splunk, Prometheus, and OpenTelemetry
• Refactor and enhance Prometheus metrics to scale reliably under high-traffic conditions
• Collaborate cross-functionally on backend priorities spanning performance, reliability, and security

The Person:

• Recent graduate with a Bachelor's or Master's in Computer Science or a related field from a top 20 CS program
• Solid Python skills with hands-on experience in FastAPI or Flask
• Familiarity with PostgreSQL, Redis, or similar databases
• Some exposure to monitoring, logging, or metrics platforms, even from coursework or personal projects
• Excited to work in a small, fast-moving team where your work ships to real enterprise customers from day one