AI Engineer

• B2B contract, full-time, 12 months + extensions
• Working model: 100% remote

We are looking for an experienced AI Engineer to design, build, validate and maintain production-grade LLM-based solutions for clinical and life-sciences use cases.

The role combines hands-on GenAI engineering with strong Databricks, MLflow, LLM observability and GxP validation practices. You will work on AI solutions that require not only strong technical performance, but also traceability, reproducibility, documentation, controlled releases and audit readiness.

Your responsibilities

• Designing, developing, validating and maintaining LLM-based solutions for clinical and life-sciences use cases.
• Building prompt workflows, RAG solutions, tool integrations, guardrails and human-in-the-loop mechanisms.
• Designing and maintaining knowledge graphs and graph-based AI solutions using technologies such as Neo4j.
• Building controlled end-to-end AI pipelines in Databricks.
• Supporting data ingestion, preparation, model integration, evaluation, deployment and monitoring.
• Integrating AI solutions with MLflow to capture:
• model and prompt versions,
• parameters,
• datasets,
• evaluation results,
• approvals,
• lineage,
• deployment records,
• associated technical artifacts.
• Using Langfuse for LLM observability, tracing and performance monitoring.
• Investigating unexpected model behaviour and supporting root cause analysis.
• Establishing end-to-end traceability across requirements, data, prompts, models, tests, approvals, releases and production changes.
• Applying GxP principles and internal quality procedures across the full solution lifecycle.
• Supporting validation planning and execution, including requirements, specifications, risk assessments, test protocols and traceability.
• Maintaining audit-ready documentation and objective evidence.
• Supporting data integrity, reproducibility, version control and controlled access.
• Defining and executing LLM evaluation strategies covering accuracy, grounding, consistency, robustness, safety and operational reliability.
• Communicating technical behaviour, limitations, validation status and compliance risks to both technical and non-technical stakeholders.

Must-have experience

• 2-5 years of professional experience in AI, Machine Learning or a related field.
• Master's degree or PhD in Computer Science or a related technical discipline.
• Strong hands-on experience with Databricks.
• Practical experience developing LLM / Generative AI solutions.
• Experience with RAG, prompt workflows and LLM evaluation.
• Hands-on experience with MLflow.
• Experience with graph technologies and preferably Neo4j / Knowledge Graphs.
• Understanding of production AI pipelines, model deployment and monitoring.
• Practical familiarity with GxP-regulated environments.
• Understanding of validation, traceability, documentation and audit-readiness requirements.
• Strong Python skills.
• Experience working with version control and controlled software delivery processes.
• Strong communication and documentation skills.

Nice to have

• Experience with Langfuse or other LLM observability platforms.
• Experience with GraphRAG.
• Previous work within pharma, biotech, clinical research or life sciences.
• Knowledge of Computer System Validation / Computer Software Assurance.
• Familiarity with 21 CFR Part 11, Annex 11, ALCOA+ or similar data integrity requirements.
• Experience with Azure-based AI services or Azure OpenAI.