I design and ship production AI systems on AWS — for teams in healthcare, life sciences, edtech and aviation.

Multi-brand Open edX learning platform

A revenue-generating learning platform built so one deployment can run several brands and both direct (B2S) and partner-mediated (B2B2S) enrolment. ISAGS launches first; further brands switch on through configuration rather than a rebuild.

• Authored the full Statement of Work: six sprints, 53 man-days, eight payment milestones, change-request policy and acceptance criteria
• AWS foundation from day one — dedicated account, least-privilege IAM, budgets, CloudTrail, GuardDuty, encrypted EBS, AWS Backup
• Open edX via Tutor on EC2, with brand segregation through native Organisations; ReactJS institutional site and storefront; Razorpay checkout
• FastAPI middleware for SSO, enrolment sync and a five-role RBAC matrix; brand-aware PDF certificates with QR verification
• CI/CD through CodePipeline and GitHub Actions, independent VAPT, and a Brand Activation Playbook so the client's team can onboard new brands alone

AlphaGutScan — sample-to-outcome microbiome pipeline

A universal six-stage pipeline that turns a lab sample into a clinical outcome report, with five quality gates in between. Deployed in Frankfurt alongside the client's bioinformatics workloads on AWS HealthOmics.

• Owned the knowledge-graph workstream on a 12-week proof of concept
• Wrote the complete prompt library (P0–P6), from metadata intake through chatbot guardrails
• Designed a domain-pack / frozen-skeleton architecture so the same pipeline serves new test types without re-engineering
• Consolidated model usage onto a single Claude model on Bedrock for cost and consistency

Orion — aviation intelligence platform

A GraphRAG system for aviation knowledge, scoped and documented from the ground up. The Statement of Work was written to AWS partner-funding standards, framing every deliverable as design, build and deploy.

• Full SoW and architecture for a Neptune + vector + Bedrock Knowledge Base retrieval pipeline
• Established the GraphRAG pattern that was then reused on AlphaBiomics — one architecture, two industries

Life sciences AI workflows

Three productised workflows built to be licensed many times over rather than rebuilt per customer.

• Clinical-trial patient recruitment — TrialGPT-style matching on the Chia and TREC 2021 datasets, with a metabolic-disease demo
• Pharmacovigilance — adverse-event analysis over FAERS with MedDRA coding
• Regulatory submissions — NDA dossier assembly in CTD structure, tested against a synthetic drug dossier and lab reports
• IAM design for the Amplify and AgentCore deployment, including resolving managed-policy quota limits

Industry-trends report generator

A serverless pipeline that researches a sector, grounds the findings in a knowledge base and produces a formatted PDF report. I own production support and shipped a full rewrite after tracing a corrupted report back to a knowledge-base aggregation leak.

Group IT platforms

Running the shared IT estate across three organisations: AWS accounts and billing, Google Workspace, DNS, security baselines and vendor onboarding. Hired and now lead a small engineering intern team focused on API work, Python and AWS.