My work combines backend services, AI workflows, product interfaces, and research-informed delivery across real project constraints.
Software Engineer focused on AI-powered products
$payload read portfolio-pageMy Projects So Far
$node scripts/render-featured-work.mjs3 featured cards from 3 published projects
$cms media:checkuploaded images resolve for cards and project detail media
$git status --shortSoftware Engineer focused on AI-powered products
Selected work
An AI-augmented qualitative coding platform that helps researchers maintain coding consistency through real-time audit alerts, deterministic embedding similarity, constrained LLM feedback, visual analytics, and collaborative inter-coder reliability workflows.
Built and evaluated Double DQN limit-order trading agents in the Bristol Stock Exchange simulator to test how reward design changes execution behaviour. The study showed that surplus-based rewards produced a more disciplined “earn the spread” policy with a higher Sharpe ratio, while profit-based rewards encouraged aggressive spread-crossing and more trades but weaker risk-adjusted returns.
AuthLens is a full-stack AI workflow platform that helps healthcare teams prepare prior authorization and appeal packets from synthetic or de-identified PDFs. It turns payer policies, denial letters, and patient-supporting documents into structured criteria, evidence matches, readiness reports, citation-checked drafts, audit logs, and exportable review packets.
I build applied AI and backend-heavy software with clear product framing, reliable interfaces, and recruiter-facing evidence of how the work was delivered.
I am refining a Payload-backed portfolio that turns project records into focused case-study pages, faster media previews, and cleaner recruiter-facing content.
Send a role, project brief, or technical challenge. I can respond with relevant project evidence, stack fit, availability, and next steps.