About this role

Ownership of core parts of the AI architecture
Design and development of scalable AI agent systems (multi-step reasoning, decision pipelines, tool use)
Responsibility for reliability & quality of AI outputs (evaluation, monitoring, guardrails)
Further development of LLM systems (prompting, fine-tuning, tooling, memory, orchestration)
Building observability & evaluation frameworks (regression tests for AI)
Close collaboration with business & product teams to deliver real impact
Make technical decisions with long-term impact

6–8+ years of experience in software engineering (ideally with experience in AI/LLM environments)
Very strong Python skills (Django or equivalent)
Experience with: LLM APIs (OpenAI, Claude, etc.), AI system design
Evaluation methods & observability
Ability to make AI reliable and to balance trade-offs between speed & quality
Highly autonomous and self-motivated work style

Flexible working hours
Remote / home office options
Workation available under certain guidelines
Regular team events — from boat tours and escape rooms to climbing parks and vision workshops
Mental health offerings and workshops
Transparent high-performance model
Support with parental leave applications
Corporate benefits program with discounts, including Zalando, Apple, Aida
Free Urban Sports Club membership
Integrity, trust and responsibility are part of the company culture

Senior Full Stack Developer – Remote

Key skills