YOUR ROLE

• Design, develop and deploy AI solutions on Databricks – from LLM-based applications and RAG pipelines to AI agents – and take them from prototype to production.
• Build and orchestrate agent workflows using the Databricks Mosaic AI Agent Framework or frameworks such as LangChain / LangGraph.
• Implement retrieval solutions with Databricks Vector Search, embeddings and well-structured knowledge sources.
• Deploy and serve models and agents with Databricks Model Serving, using MLflow for tracking, versioning and registry.
• Evaluate and monitor AI solutions for quality, accuracy, latency, cost and safety.
• Apply governance, access control and lineage to AI assets using Unity Catalog.
• Integrate AI solutions with applications and APIs, including apps hosted as Databricks Apps.
• Manage code in GitHub and follow CI/CD, MLOps / LLMOps and documentation best practices.
• Work closely with data engineers, data scientists and stakeholders to translate business needs into AI solutions.

YOUR PROFILE

• 6–8 years of software, data or ML engineering experience, including hands-on Databricks experience.
• Practical experience with Databricks Mosaic AI and Unity Catalog – Mosaic AI is the key skill for this role.
• Strong Python and good SQL; working knowledge of PySpark.
• Hands-on experience building LLM applications, RAG and agents in production, using at least one agent / orchestration framework (e.g. LangChain / LangGraph, Mosaic AI Agent Framework).
• Hands-on experience with MLflow, Databricks Vector Search and Model Serving.
• Experience with REST APIs and Git / GitHub with CI/CD workflows.
• Experience of working alongside data scientists.
• Strong communication skills and the ability to work with international clients; very good English.
• Bachelor's or Master's degree in Computer Science, IT or a related field.