Prompt & Context Engineering: Design, test, and refine complex prompts and context-management strategies to maximize the performance and reliability of LLM-powered features.
Data security and governance: Handle client data in line with the firm's data security, client-data confidentiality and responsible AI requirements, and raise risks or issues promptly.
Integrate the digital stack. Connect models and AI services with enterprise platforms, data sources, workflow systems, user interfaces and upstream or downstream applications.
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
Data security and governance: Handle client data in line with the firm's data security, client-data confidentiality and responsible AI requirements, and raise risks or issues promptly.
Domain expert: You’ve scaled AI products in production and design for LLM failure modes such as hallucination, context degradation, prompt injection and latency under load.
Infrastructure & Engineering Excellence: Manage infrastructure and CI/CD pipelines while ensuring scalability, performance, security, and high code quality through best practices and governance.
Own the technical architecture end to end, including model and platform selection, agent orchestration, evaluation, security and integration with Lenovo systems.
Apply AI-native engineering practices by structuring work for AI agents, providing clear context and constraints, and critically validating the outputs.