26 days ago
Remote, Germany or Remote, RomaniaStaff+
Responsibilities
- Own AI capabilities from problem discovery and technical design through implementation, evaluation, release, production monitoring, and continuous improvement.
- Build and review production software across AI services, APIs, connectors, background services, MCP-compatible tools, data pipelines, and product surfaces.
- Design pragmatic agentic systems using retrieval and grounding, structured outputs, tool execution, model routing, state and context management, approvals, fallbacks, and graceful degradation.
- Develop data and platform foundations including APIs, event streams, ingestion and transformation, data quality, metadata, storage, observability, and governance.
- Create end-to-end prototypes, validate them against real workflows, and evolve successful patterns into secure, maintainable, multi-tenant product capabilities.
- Build datasets, automated and human-reviewed evaluations, trace analysis, regression gates, and telemetry for AI quality, latency, safety, cost, and task completion.
- Engineer enterprise trust through tenant isolation, least-privilege access, identity and authorization, auditability, data minimization, prompt-injection defenses, human approval, feature flags, and safe rollback.
- Collaborate across Product, Design, Architecture, Security, Support, Customer Success, and engineering teams while mentoring developers and creating reusable libraries and reference implementations.
Requirements
- 7+ years of professional software engineering experience or equivalent evidence of senior/principal-level production impact.
- Demonstrated experience shipping and operating customer-facing production software beyond notebooks, proofs of concept, demos, or advisory work.
- Professional proficiency in Python and strong ability in at least one product-engineering language such as C#, TypeScript, or Java.
- Hands-on experience building production LLM or agentic applications, including areas such as retrieval and grounding, embeddings, hybrid search, structured outputs, tool calling, context and state management, model routing, or human approval.
- Experience with data-intensive systems, APIs and integrations, event or streaming data, ingestion and transformation, data quality, metadata, storage, and operational observability.
- Strong system-design fundamentals for API-first, distributed, cloud-native, multi-tenant SaaS products and secure enterprise integrations.
- Practical experience evaluating and diagnosing AI systems using datasets, traces, qualitative review, quantitative metrics, automated tests, CI/CD, and production telemetry.
- Ability to make pragmatic architectural decisions, communicate clearly, translate ambiguous needs into testable plans, and drive outcomes across team boundaries.
- A degree in computer science, software engineering, AI/ML, or a related field, or equivalent practical experience.
- Preferred experience includes enterprise AI platforms, Microsoft Azure, Azure OpenAI or Microsoft Foundry, Semantic Kernel, MCP, agent orchestration, vector or hybrid search, OpenTelemetry tracing, hosted and open-source models, hybrid or on-premises deployments, enterprise product modernization, European data-sovereignty and responsible-AI requirements, mentoring, and agentic development tools.
Benefits
- Flexible hybrid work model combining office and home.
- Personalized learning journeys, mentorship, and opportunities for professional growth.
- Time and support to learn, experiment, and improve engineering practices.
- Paid Social Day for community or charitable support.
- Regular opportunities to connect and share knowledge across European teams.
- Competitive, location-specific benefits package.
Tech Stack
Categories
