Staff AI Engineer
Blue Yonder4 days ago
Hamburg, GermanyStaff+
Responsibilities
- Architect and build software systems for AI-agent development, evaluation, deployment, and continuous improvement.
- Develop services and pipelines for agent traces, tool calls, workflow outcomes, user feedback, and other production signals.
- Build scalable systems for deterministic and model-based evaluation, statistical analysis, human review, regression testing, and failure classification.
- Create training and evaluation environments with stable APIs, tools, simulations, resettable scenarios, and reproducible state.
- Implement enterprise-system integrations and supporting services for agents operating across domain data and multi-step workflows.
- Partner with model-training teams to integrate models, investigate failures, and translate production evidence into engineering and evaluation improvements.
- Improve reliability through observability, automated testing, failure recovery, safe rollouts, and clear launch criteria.
- Provide technical leadership through system design, code review, documentation, mentoring, and cross-team direction.
Requirements
- Around eight or more years of software engineering experience or equivalent depth, with experience delivering complex production systems.
- Strong Python and backend engineering expertise, including API design, distributed systems, data processing, automated testing, and maintainable service architecture.
- Hands-on experience building LLM-powered applications, AI agents, machine learning platforms, or similarly complex systems.
- Practical understanding of AI evaluation, including test-case design, trace analysis, failure classification, regression testing, and measurement of nondeterministic systems.
- Strong software engineering fundamentals, including code quality, security, observability, CI/CD, and operational reliability.
- Experience with cloud platforms such as Azure, AWS, or GCP, containerization, and modern deployment practices.
- Ability to collaborate with researchers and model-training engineers and translate experimental needs into production software.
- Strong technical judgment, communication, and ability to provide direction in ambiguous problem spaces.
- Preferred experience with supervised fine-tuning, preference optimization, reinforcement learning, reward or verifier design, checkpoint evaluation, model-training environments, simulators, evaluation harnesses, or agent development platforms.
- Preferred understanding of training and evaluation data practices, including curation, synthetic data, provenance, versioning, quality control, and data-leakage prevention.
- Experience with supply chain, retail, or other enterprise environments involving complex workflows, permissions, business constraints, and human approval paths is preferred.
Tech Stack
Categories
About Blue Yonder
Blue Yonder builds cloud-based supply chain software for retailers, manufacturers, and logistics providers, covering demand forecasting and replenishment, price optimization, order management, and warehouse and transportation management. Headquartered in Scottsdale, Arizona, it delivers its enterprise SaaS platform on Microsoft Azure and supports large, global operations. The company traces its roots to JDA Software, which rebranded as Blue Yonder, and serves customers across retail, manufacturing, and logistics markets.