Helping a customer implement a large language model, geared to solving complex and advanced business challenges.
Deploying an end-to-end ML pipeline to streamline and automate the AI offerings of some of the largest organisations in the world.

Proven experience designing and deploying GenAI and agentic AI solutions using tools such as Databricks Mosaic AI Agent Framework, Azure AI Studio, and Azure OpenAI Service.
Expertise in building production‑grade RAG pipelines, including chunking strategies, vector search, retrieval evaluation, and end‑to‑end optimisation.
Hands‑on experience with Large Language Models (LLMs) in enterprise environments, including prompt engineering, fine‑tuning, guardrail implementation, and responsible AI practices.
Ability to develop and deploy AI agents with tool use, memory, and multi‑step reasoning using frameworks like LangChain, LangGraph, Semantic Kernel, or CrewAI.
Strong LLMOps and MLOps skills, including model evaluation, A/B testing, monitoring, and CI/CD for AI workflows (e.g., Databricks Asset Bundles, GitHub Actions, Azure DevOps).
Proficiency in writing production‑quality Python, with the ability to support AI projects from initial prototype through to production deployment.
Knowledge of AI governance and compliance, including responsible AI principles, bias testing, and maintaining audit trails suitable for regulated industries.
Excellent communication skills, able to explain complex AI architectures to senior leaders while also collaborating deeply with engineering teams to troubleshoot technical issues.

AI Consultant

Key skills