Ml Engineer

• Design, implement, and maintain scalable data ingestion pipelines for unstructured and structured content.
• Build and manage vector database infrastructure (e.g. Pinecone, Milvus) for document indexing and retrieval.
• Develop and enforce fine-grained access control mechanisms to ensure secure and compliant knowledge access.
• Collaborate with domain experts to source, curate, and structure knowledge for RAG workflows.
• Integrate document chunking, embedding generation, and metadata tagging into the pipeline.
• Monitor and optimise retrieval performance, latency, and quality across the RAG stack.
• Implement observability, logging, and evaluation metrics for pipeline health and retrieval quality.
• Work with IT teams to deploy and maintain services in a self-hosted environment.

Job requirements:

• Bachelors or Masters degree in computer science, Data Engineering, or a related field.
• 5-8 years of experience in ML Engineering, Data Engineering, or MLOps.
• Proficiency in Python and experience with data manipulation, analysis and visualisation libraries (e.g. Pandas, NumPy, Matplotlib, Seaborn etc.)
• Hands-on experience with vector databases and embedding techniques, data pipelines
• Familiarity with access control models (e.g. RBAC, ABAC) and data governance practices.
• Strong understanding and adherence to the Clean Code principles.

Preferred Qualifications

• Experience with Retrieval-Augmented Generation (RAG) architectures.
• Hands on experience with AI-Aided software development (e.g. GitHub Copilot, Cursor, Claude Code)
• Knowledge of SQL and relational database designs. (e.g. PostgreSQL)
• Familiarity with LangChain, LlamaIndex, or similar frameworks.
• Exposure to knowledge management systems or enterprise search platforms.
• Understanding the basics of ISO 27001.
• Experience with containerisation (Docker, Kubernetes).
• Experience with ML/AI frameworks (e.g. SciKit-learn, Keras, PyTorch, TensorFlow).