Senior Backend Engineer, AI Platform
At Navigara, we’re on a mission to bring clarity and intelligence to software engineering teams. Engineering orgs are pouring money into AI coding tools and almost none of them can say what came back. Our platform answers that: what the tokens bought, where the leverage is real, and which teams are actually shipping faster because of it.
We’re looking for a Senior Backend Engineer to build the AI platform underneath that. You’ll own the ingestion and enrichment pipelines that turn raw agent, model and repository activity into signal, the LLM services our product features call, and the model router that picks the cheapest model that still gets the answer right.
This is systems work with a model in the loop. Non-determinism, cost per call, latency budgets, evals and drift are first-class engineering concerns here, not an afterthought bolted onto a normal backend.
This is a hybrid role based at our engineering office in Brno, Czechia. We expect you on site for the days the team needs to be in the room together, and trust you to work remotely the rest of the time.
What you’ll do
- Design and implement scalable backend services in TypeScript or Go
- Build data pipelines that process millions of agent, model and repository events
- Own LLM services in production: prompt and context assembly, tool calling, streaming, retries, caching
- Build and tune our model router so the right model handles each job at the lowest defensible cost
- Instrument token spend and quality end to end so AI ROI is measured, not asserted
- Stand up evals and regression harnesses that catch model and prompt drift before customers do
- Contribute to architecture decisions, and mentor engineers on building with models
What we’re looking for
- 5+ years of backend engineering experience
- Strong proficiency in TypeScript/Node.js or Go
- Shipped and operated LLM-backed services in production, including their failure modes
- Experience with PostgreSQL and data modeling, plus embeddings or vector search
- Comfort reasoning about cost, latency and quality as a single trade-off
- Familiarity with cloud services (AWS, GCP, or similar)
- Excellent problem-solving and communication skills
Nice to have
- Built agentic systems: multi-step tool use, orchestration, durable long-running tasks
- Experience with data processing at scale and event-driven architectures
- Worked on eval infrastructure, LLM observability, or inference cost optimization
- Background in developer tools or analytics platforms
- Open source contributions
Our engineering team is based in Brno, Czechia and works hybrid out of our office. What unites us is relentless focus, fast execution, and our passion for software craftsmanship in a stack where models are now part of the runtime.
Ready to join our team?
Click below to submit your application. We read every message and reply within a week.