Transitioning GenAI prototypes (e.g., RAG applications, agents, or tooling) into stable, production-ready services such as APIs, backends, or workers — including architecture, error handling, and technical documentation
Building reliable data and document pipelines (ingestion, transformation, indexing/embeddings, retrieval) as core components for production-ready AI solutions
Developing and establishing comprehensive testing and quality strategies (unit, integration, and end-to-end tests) as well as LLM-specific evaluation and regression mechanisms (evaluation sets, guardrails, versioning)
Designing and operating CI/CD pipelines, environments (Dev/Test/Prod), and release processes to ensure reliable deployment of GenAI-based services
Implementing modern observability (logging, tracing, metrics, dashboards, alerts) and enforcing security and governance standards (identity/RBAC, secrets management, policies)
Requirements
Degree in Computer Science, Information Systems, or a comparable qualification
Several years of experience in software engineering, ideally with a focus on Python; additional experience with TypeScript, Java, or C# is a plus
Experience in production development of backend services, including testing, CI/CD, and integration landscapes
Strong technical understanding of operating and stabilizing production systems—especially monitoring, alerting, incident readiness, and awareness of performance and cost
Hands-on experience with cloud technologies, preferably Microsoft Azure (identity, secrets management, storage/compute, basic networking)
Structured, quality-oriented work style and a commitment to delivering high-quality, scalable GenAI solutions into production