Staff / Senior AI Product Engineer
Productboard Zobrazit všechny práce
- Brno, Jihomoravský
- Trvalý pracovní poměr
- Plný úvazek
- Access from day one. Every engineer and leader gets the best tools available — Cursor, Claude Code, Codex, and more.
- AI Champions across teams. Dedicated experts embedded in teams to pair, unblock, and help you move faster with AI agents.
- A codebase built for agents. Structured AGENTS.md files, curated skills, and clean patterns so AI agents can work effectively alongside engineers.
- Serious investment in DevX. We continuously improve our developer tooling so testing, prototyping, and working with agents is seamless.
- Dedicated AI days. Every six weeks, Engineering, Product, and Design teams get focused time to ship real features using AI tools and push boundaries.
- Agent native architecture standards: clear API contracts, semantic naming, and well-defined module boundaries that keep AI effective as systems grow.
- A context infrastructure layer with repo versioned guidance that AI tools automatically load, improving the output of Cursor, Claude Code, and Codex simultaneously.
- AI agent workflows for on-call and incident resolution: triage alerts, pull logs, surface relevant history, and suggest remediation.
- Systematic optimization of AI code review to catch correctness, security, and maintainability issues earlier.
- Building AI-powered product features.
- Enhancing and sustaining our internal tech stack, while identifying and incorporating new state-of-the-art technologies.
- Discovering and experimenting across different domains, creating MVPs and POCs, engaging in discussions about findings with fellow engineers and the product team, and planning the execution.
- Make our codebase AI-ready: define clear module boundaries, improve API contracts, add semantic context, and build the structured documentation that makes AI agents more effective across every repo.
- Design and implement agent workflows that go beyond chat: multi-step reasoning, tool use, autonomous task execution, and human-gated checkpoints.
- Run experiments, validate with real users, and iterate based on evidence. We measure learning velocity, not just output.
- Collaborate closely with product managers and designers to shape what we build, not just how we build it. We expect a product mindset, not just technical execution.
- Act as a knowledge multiplier, sharing what you learn across and beyond your team to raise the bar for everyone.
- 7+ years of professional software engineering experience, with a proven track record of shipping scalable production systems.
- Deep hands-on experience with LLMs in real products — including prompt design, context management, evaluation, and understanding real-world limitations (hallucinations, latency, cost, reliability).
- Experience building agentic systems is highly valued. Alternatively, deep hands-on work with advanced LLM workflows (tool use, multi-step reasoning, memory, orchestration) and a clear understanding of their trade-offs — along with the drive and technical maturity to quickly evolve toward agentic architectures.
- You think like a builder - ideally a former founding engineer or founder - with a strong instinct for shipping what truly moves the product and the company forward.
- You’re drawn to agent-native architecture and believe this is where software is heading. You’re excited to rethink codebases, APIs, and documentation so AI agents can reliably operate and scale.
- You rely on AI tools daily (e.g., Cursor, Claude Code) and treat them as a core part of your engineering workflow — constantly experimenting, refining prompts, and pushing them to meaningfully increase your speed and output.
- Comfortable working in distributed systems and event-driven architectures (e.g., queues, async processing, service-to-service communication).
- Able to lead complex technical initiatives end-to-end, raising the bar for architecture, quality, and engineering culture.
- AI Layer: Python, Pydantic AI, Braintrust
- Frontend: TypeScript, React, Relay, GraphQL
- Backend: Kotlin, Ruby, Kafka
- Storage: PostgreSQL, MongoDB, Elastic, Redis
- Data Pipeline: Python, Keboola, Looker, Snowflake
- Infrastructure: AWS, Cloudflare, Kubernetes, Terraform
- Business tools: Slack, Jira, Google suite, Zoom, Notion