Collaboration & Delivery: Work with Product Owner, Developers, Quality Engineers and UX Designers to deliver the Virtual Companion. Contribute to sprint planning, code reviews and documentation.
Generative AI & LLMs: Hands-on experience building production LLM applications and designing agentic systems: prompt and context engineering, retrieval-augmented generation (including graph-based retrieval), tool use, state and control flow design, orchestration frameworks, and the tracing, guardrails, and evaluations that make them reliable. Basic knowledge of fine-tuning, parameter-efficient adaptation, dataset construction, and evaluation.
Work directly with the CEO, who has built and run multiple award-winning companies across several industries over 17 years. One decision maker, no committee. Your job includes challenging the brief where the brief is wrong, and you will get a straight answer either way, quickly.
Feature Engineering Pipeline: Design, build and maintain reliable feature engineering pipelines on Databricks and AWS for ingesting, transforming, validating and serving structured and unstructured data used by ML/AI workloads.
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.
Prompt & Context Engineering: Design, test, and refine complex prompts and context-management strategies to maximize the performance and reliability of LLM-powered features.
Troubleshoot complex issues, providing timely resolutions to consolidate system product reliability and performance before production team ships good products to customers.
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