Staff Backend Product Engineer (Prague/Brno/Remote EU)

What you'd build

• Agent-native architecture standards. Clear API contracts, semantic naming, well-defined module boundaries. The patterns that keep AI effective as our systems grow.
• A context infrastructure layer. Repo-versioned guidance that AI tools load automatically — improving the output of Cursor, Claude Code, and Codex simultaneously.
• Self-healing workflows for incidents. Agents that triage alerts, pull logs, surface relevant history, suggest remediation. Humans intervene where judgment matters.
• Agent workflows that go beyond chat. Multi-step reasoning, tool use, autonomous task execution with human-gated checkpoints — for product features, not internal demos.
• Systematic optimization of AI code review. Earlier detection of correctness, security, and maintainability issues, with the noise filtered out before it reaches a human reviewer.

The role

How we work

• One named driver per initiative. End-to-end ownership of the outcome, the path, the decisions, and the learnings. No approval chains. The driver decides; leadership unblocks.
• One-page pre-reads as the unit of decision. Big work starts with a brief covering the problem, expected outcome, risks, and effort. Leadership reads it and decides. No 30-slide decks. No two-week alignment cycles.
• Continuous delivery, no quarterly planning. Roadmap committed one month out. Beyond that, AI moves too fast for longer cycles to mean anything. We ship to internal first, then beta, then GA. Validation comes from real usage.
• PMs and designers ship to production. Not just specs and Figma. They prototype with AI tools and ship alongside engineers. PMs own what gets built and when. Engineers own how.

The system around you

• Best AI tools from day one. Cursor, Claude Code, Codex, Glean. No waiting list, no approval process. If a better tool shows up tomorrow, you get that one too.
• AI Champions embedded on every team. Engineers (not coordinators) who pair with you, unblock you, and help you move faster with agents. Four hours every week dedicated to team enablement.
• A codebase built for agents. Curated AGENTS.md files, repo-versioned skills, clean contracts. Continuously evaluated, not accumulating.
• Ship It with AI days. Two days every six weeks. No meetings for ICs. Pick a real problem, try a new AI workflow, ship to production within 48 hours.
• Knowledge that compounds. Monthly engineer-to-engineer events where we share what we're experimenting with, learning, and shipping with AI.

Who we're looking for

• 6-10+ years of production software engineering experience
• Strong backend skills in Python, Kotlin, or Java, with experience evolving service-level logic and infrastructure
• Hands-on LLM experience in real products: prompt design, context management, evaluation, real understanding of trade-offs (hallucinations, latency, cost, reliability)
• Comfort with distributed systems and event-driven architectures (queues, async processing, service-to-service communication)
• Daily use of AI coding tools as a core part of your workflow — pushing them, refining prompts, knowing where they break

Our tech stack

• AI layer: Python, Pydantic AI, Braintrust
• Frontend: TypeScript, React, Relay, GraphQL
• Backend: Kotlin, Ruby (legacy services we're modernizing), with new services built in Kotlin
• Storage: PostgreSQL, MongoDB, Elastic, Redis
• Data pipeline: Python, Keboola, Looker, Snowflake
• Infrastructure: AWS, Cloudflare, Kubernetes, Terraform