Python, LLM, GenAI/Senior Consultant Specialist

We are currently seeking an experienced professional to join our team in the role of Senior Consultant Specialist. In this role, you will:

• Build LLM application services in Python, covering prompt strategies, tool/function calling, and workflow orchestration (e.g., LangChain/LangGraph).
• Design and implement RAG, including document/artefact ingestion (metric definitions, dimensional models, lineage, report examples).
• Implement RAG retrieval foundations: chunking, metadata strategy, embeddings, indexing, retrieval and re-ranking.
• Define grounding approaches to minimise hallucinations and ensure Finance-approved definitions are consistently applied.
• Deliver deterministic query generation aligned to the semantic layer, including constraint-driven SQL/query DSL, schema validation and guardrails.
• Implement query execution patterns such as caching, robust error handling, and safe fallback behaviours.
• Build and maintain API layers (REST/gRPC) for UI and platform integration, including authentication/authorisation and request auditing.
• Establish evaluation and operational practices: test harnesses (golden datasets, accuracy/retrieval metrics, regression tests, prompt/model versioning), LLMOps (CI/CD, config management, promotion, observability, incident runbooks), collaboration with data/platform teams, and compliance with security/privacy requirements.

To be successful in this role, you should meet the following requirements:

• Strong Python engineering capability, including clean architecture, testing, packaging, and performance optimisation.
• Proven experience delivering production LLM apps (or advanced PoCs) using major LLM APIs/hosted models (e.g., Claude, GPT, Gemini, open-weight models).
• Hands-on RAG implementation experience.
• Practical prompt engineering and tool/function calling to enable reliable LLM behaviours.
• Experience building agents/workflows and using orchestration frameworks like LangChain and/or LangGraph (or equivalents).
• Solid ML fundamentals: embeddings, vector search, evaluation methods, and awareness of common failure modes.
• API engineering skills (FastAPI/Flask), including async patterns and integration-focused design.
• Cloud-native delivery (GCP preferred): containers, serverless/Kubernetes, CI/CD, observability, plus secure engineering practices and LLM security mitigations (prompt injection, jailbreaks, data leakage).