Senior Backend Engineer

About Us

We build software that makes governance, risk, and compliance (GRC) approachable: turning dense regulatory frameworks and internal policy into something organizations can work with. AI is central to how we do that: surfacing the right information, making sense of complex documents, and keeping outputs trustworthy in a domain where accuracy matters.

We're a small team, early in the journey. The core architecture is in place and proving itself, but there's plenty left to shape. You'll have real ownership over both what you build and how it evolves. We're based in Stockholm and work hybrid.

Role Overview

You'll own and evolve the backend systems at the core of our Navigator platform: including the document processing pipeline, job execution, the retrieval and query layer, and the APIs that surface it all. You work in a Kubernetes environment, running, changing, and extending application workloads, and you think about how the system scales and where it needs to go next, not just what it does today.

You're someone who wants to grow into technical leadership. You have opinions about how things should be built, you're critical about what actually needs to be solved now, and you bring the same pragmatism to architecture as you do to delivery. You're curious about the wider system, not just your slice of it.

What You'll Work On

• The document processing pipeline: Celery-based orchestration, job execution, failure handling, and observability
• LLM integration: prompt engineering, structured output, multi-provider orchestration (Anthropic Claude, OpenAI, OpenRouter)
• The retrieval layer: Milvus vector store, chunking strategies, embedding quality, re-ranking
• FastAPI services and the query surface that backends the assistant
• Application workloads on Kubernetes: deploying, scaling, and evolving how backend services run
• PostgreSQL data modelling, including graph features via Apache AGE
• Contributing to how the system evolves, not just executing, but helping shape what comes next

What We're Looking For

• 5+ years building production backend services (ours is using Python); strong on typing, testing, and clean code
• Hands-on experience with LLM APIs in production: prompt design, structured outputs, evaluation, cost/latency trade-offs
• Experience with vector databases and RAG (Milvus, pgvector, or similar): embeddings, indexing, retrieval quality
• Solid experience with distributed task systems (Celery + Redis, or comparable)
• Comfortable working in and reasoning about cloud-hosted Kubernetes environments: deploying and operating application workloads with an awareness of cost and scale
• Comfort with relational databases and async web frameworks (FastAPI or equivalent)
• Opinionated about engineering quality, pragmatic about what to build now versus later
• Wants to grow: you're thinking about the wider system and where it's heading, not just your current task
• Built solutions that run on Azure (including AI Foundry, Blob Storage, AKS) or comparable experience on AWS or GCP and open to ramping up knowledge

Helpful But Not Required

• Apache AGE or other graph databases
• Exposure to regulated industries (GRC, finance, legal, healthcare)

How to Apply

Send your resume and preferably a short cover letter detailing your relevant experience and what excites you about this role to careers@nooga.net.

‍