Isaac Griffiths

I am Isaac Griffiths, a Data Engineer in GSK R&D Tech on a manager-grade job profile. I design and build internal AI tools that have to survive real users, real compliance, and a real queue, and I am now the technical lead of an agentic product, one of the first genuinely agentic systems moving towards production in this part of the business.

It started with a boring observation: generic request forms let people submit almost nothing, so engineers spend their first reply asking for what they should already have. I served as technical lead for a triage layer that asks context-aware follow-up questions at intake, so a ticket arrives actionable instead of arriving twice.

The way I work is closer to forward deployed than to a backlog. I sit with the team that has the problem and build alongside them: something working on screen inside the session, then reshaped against what they actually do with it. I am AI-native about the building itself: Claude Code writes the Python and TypeScript, and I specify the system, direct the agents, and read, review, test and debug what comes out.

Before that I spent three years as a lab IT engineer, keeping regulated scientific environments running: incident response, decommissioning, OT network segmentation, and a lot of instruments that do not tolerate downtime. That is where I learned that the interesting part of a system is what it does on a bad day.

• Aug 2026 – present

  Data EngineerCurrent

  GSK R&D Tech · Stevenage

  Technical lead of an agentic product in Scientific Data Engineering, promoted from the apprenticeship onto a manager-grade job profile (Data and Analytics Engineering Manager) four years after joining GSK. I own the product's path from working prototype through stakeholder review into production, and I still build hands-on, sat with the people who use it.

  • Agentic systems
  • Tech lead
  • AI-native
  • Python
  • TypeScript
• Sep 2025 – Aug 2026

  Agentic Engineer, Apprentice

  GSK R&D Tech · Stevenage

  Designed and shipped AI-enabled tools that improve ticket quality and reduce delays between scientists and engineers. I served as technical lead for a context-aware ticket-triage system that captures complete requests at intake, contributed to one of R&D Tech's first agentic systems moving towards production, and prototyped an agentic booking system with dashboards for resource-owning teams. I also reverse-engineered and rebuilt a compliant replacement for an internal application whose source code had been lost, verifying its behaviour directly with the scientists who use it. On the triage platform I co-authored and presented the architecture, then ran the testing cycle to production readiness: 50+ structured test cases including adversarial inputs, API test suites, trace-identifier logging and peer review on every change.

  • Agentic workflows
  • LangGraph
  • FastAPI
  • Next.js
  • Google Cloud Run
• Sep 2022 – Sep 2025

  Laboratory IT Engineer, Degree Apprentice

  GSK R&D · Stevenage

  Kept regulated laboratory environments running across specialist instruments, endpoints, and OT networks. During the CrowdStrike incident I was the first at GSK Stevenage to restore an affected lab PC, and the BitLocker approach I worked out became the site's remediation procedure, with 250+ systems restored inside two days. I led the removal of 50+ Windows 7 systems within the GSK Legacy Programme, automated the lab PC build process, supported 250+ specialist lab devices, and worked with cybersecurity teams on OT network segmentation. Eleven GSK recognitions over the three years: one Gold, one Silver, five Bronze and four peer awards.

  • Incident response
  • OT security
  • PowerShell
  • ServiceNow
  • Compliance

Languages

Python, TypeScript, JavaScript, SQL, HTML, CSSPython on the GSK triage and booking backends; TypeScript across the triage UI, the legacy rebuild, TwinList, ShipStamp and this site.

AI & agentic

LangChain, LangGraph, Prompt engineering, Structured outputs, Tool calling, OpenAI, Anthropic, GeminiLangGraph state machines on the GSK triage agent (2025) and booking agent (2026), with an MCP server into ServiceNow. GPT-4o via Azure and Gemini at GSK; Claude in TwinList.

Web & APIs

Next.js, React, FastAPI, PostgreSQL, REST APIs, Electron, Integration designFastAPI behind the triage and booking agents; Next.js on the triage UI, booking dashboards and the legacy rebuild; PostgreSQL with pgvector and Electron in TwinList and ShipStamp.

Working with stakeholders

Embedded delivery, Pair-building, Requirements by demonstration, User testing, Adoption & handoverEvery GSK build since 2025: requirements settled with scientists in the room, then UAT, sign-off and training across lab teams.

Automation

n8n, Workflow orchestration, Process automation, ServiceNowServiceNow through the triage agent at GSK; n8n at home for the AI news digest that feeds my content.

Cloud & delivery

Google Cloud Platform, Microsoft Azure, GitHub, Cloudflare, DockerTriage agent in Docker on Cloud Run via GitHub Actions and Artifact Registry, Azure OpenAI through GSK's gateway; Cloudflare Workers, D1 and Pages for the products and this site.

AI-native development

Claude Code, GitHub Copilot agent, Cursor, Codex, Ollama, Open WebUI, Rapid prototyping, Review, testing and debugging of generated codeAt GSK: Cursor at the start in 2025, then the Copilot coding agent, now Claude Code only. At home: Claude Code, Cursor, Codex and a self-hosted model on an old gaming GPU.

Infrastructure

Windows & Linux, Networking & VLANs, Active Directory, WDS/MDT imaging, PowerShell, OT segmentation, Proxmox, UnraidThree years in GSK's Stevenage labs: PC build automation, instrument networking, OT segmentation, the CrowdStrike recovery. Proxmox and Unraid at home.

Things I have used to ship something real, not things I have read about.

• 2022 – 2026

  BSc (Hons) Digital and Technology Solutions

  Software Development specialism · Anglia Ruskin University, Peterborough

  Degree apprenticeship, completed alongside full-time delivery at GSK.

  Predicted First · 330 of 360 credits complete, seven modules at First. Final classification confirmed 10 September 2026.

  Selected results

  Programming and Networking IoT Project

  83%

  Computer and Network Technologies

  83%

  Information Security Management and Governance

  81%

  Object Orientated Modelling and Data Design

  76%

  Enterprise Analytics

  75%

  BTEC ICT: Distinction* (Claires Court School, 2022). A Level Geography: B (Claires Court School, 2022). 10 GCSEs, grades 5–8 (including Maths (8) and ICT (8)).