Engineering Lead

Unleash Innovation at the Intersection of AI, Cloud-Native Systems & DevOps Hybrid opportunity in Kraków — 4 days remote per week. As an Engineering Lead, you will be working for our client, a pioneering technology company shaping the future of intelligent systems. You will lead the design and delivery of production-quality AI services, develop agentic systems, and optimize DevOps pipelines within a modern cloud-native environment, driving impactful innovations in large language models (LLMs) and automation. Your main responsibilities: Lead the development, deployment, and maintenance of high-quality production AI services, ensuring alignment with business controls.Design, optimize, and iterate prompts for a broad spectrum of LLM use cases including instruction following, structured output, classification, summarization, and code generation.Build and manage prompt libraries with versioning strategies, treating prompts as critical engineering artifacts.Collaborate with product and domain teams to translate business needs into precise prompt specifications and AI workflows.Architect and implement agentic AI systems such as autonomous agents, multi-agent pipelines, tool-use workflows, planning loops, and memory-augmented reasoning modules.Enhance observability of LLM operations through logging, tracing, evaluation pipelines, and safety guardrails, maintaining system reliability.Provide expertise on responsible AI deployment, integrating output validation, human-in-the-loop design, and risk mitigation strategies. You’re ideal for this role if you have: At least 7 years of experience in software engineering, with a focus on AI or cloud-native solutions.Strong proficiency in Java / Spring Boot, including REST APIs, event-driven services, security, and performance tuning.Solid React development skills and experience with API integration.Hands-on experience working with relational and in-memory databases such as PostgreSQL and Redis.Experience with messaging and streaming platforms like Kafka or equivalent.Proven expertise engineering prompts for production LLM applications, understanding of tokenization, context limits, temperature tuning, and model-specific parameters.Familiarity with prompt evaluation frameworks and tooling (e.g., PromptFlow, LangSmith, Braintrust) or custom evaluation pipelines.A good understanding of Kubernetes deployments, services, ingress, Helm, Kustomize, HPA, and RBAC.Experience with CI/CD pipelines (GitHub Actions, GitLab CI, Jenkins) and Infrastructure as Code (Terraform).Hands-on knowledge of cloud platforms such as AWS, GCP, or Azure. It is a strong plus if you have: Certifications or experience integrating AI in enterprise environments.Background in responsible AI practices, output validation, and human-in-the-loop systems. Language Required for the role: Fluent English, with excellent communication skills. Eligibility for the role: Only candidates with an existing legal right to work in the European Union will be considered for this role.