Define and implement the "Definition of Done" for AI using quantitative evaluation. Use evaluation tools (e.g. DeepEval) to score models on Faithfulness and Relevancy. Use these metrics to validate model upgrades and cost-optimisation experiments
Conduct research and stay up to date with the latest advancements in AI and machine learning, integrating new technologies and methodologies into the team’s workflows.
Own the architecture and the deployment. Define how our generative AI systems are structured and integrate with our computer vision stack, and take models from experiment to production.
Develop the foundational platform for AI Agents - including agent registry, evaluation framework, prompt management, vector stores, memory layers, and tool integrations
Build proposals and solution narratives: produce technical sections, scope, effort estimates, risk assessments, and delivery roadmaps aligned to client outcomes.