I’m James Quinn, a Senior AI Engineer specializing in production-grade Agentic AI and Generative AI systems for regulated, enterprise environments. Over seven years I’ve built and operated LLM-powered systems at Google, Microsoft, and across the UK public sector, with hands-on expertise in agent orchestration, RAG pipelines, Python automation, evaluation, and live-service AI governance. I own delivery end-to-end—from architecture and orchestration logic through to deployment, monitoring, and continuous optimization in production. I enjoy collaborating with policy, legal, and product teams to harden capabilities, implement guardrails and safeguards, and ensure reliable, compliant AI that delivers real value to users and stakeholders.

James Quinn

I’m James Quinn, a Senior AI Engineer specializing in production-grade Agentic AI and Generative AI systems for regulated, enterprise environments. Over seven years I’ve built and operated LLM-powered systems at Google, Microsoft, and across the UK public sector, with hands-on expertise in agent orchestration, RAG pipelines, Python automation, evaluation, and live-service AI governance. I own delivery end-to-end—from architecture and orchestration logic through to deployment, monitoring, and continuous optimization in production. I enjoy collaborating with policy, legal, and product teams to harden capabilities, implement guardrails and safeguards, and ensure reliable, compliant AI that delivers real value to users and stakeholders.

Available to hire

I’m James Quinn, a Senior AI Engineer specializing in production-grade Agentic AI and Generative AI systems for regulated, enterprise environments. Over seven years I’ve built and operated LLM-powered systems at Google, Microsoft, and across the UK public sector, with hands-on expertise in agent orchestration, RAG pipelines, Python automation, evaluation, and live-service AI governance.

I own delivery end-to-end—from architecture and orchestration logic through to deployment, monitoring, and continuous optimization in production. I enjoy collaborating with policy, legal, and product teams to harden capabilities, implement guardrails and safeguards, and ensure reliable, compliant AI that delivers real value to users and stakeholders.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
See more

Language

English
Fluent

Work Experience

AI Architect / Senior AI Engineer (Contract) at Bournemouth University
May 1, 2025 - December 1, 2025
Technical lead for enterprise AI assistants supporting Student Services and IT in a regulated public-sector environment; designed end-to-end agentic AI architectures, coordinated multiple task-specific agents via custom middleware; architected production RAG pipelines with automated ingestion, validation, safe chunking, and deduplication over governed data sources; built Python-based automation pipelines (Azure Functions) to maintain data freshness and reduce operational overhead; implemented evaluation and monitoring frameworks tracking answer quality, failure modes, and behavioural drift; embedded Responsible AI safeguards into live systems, including welfare escalation, PII handling, content moderation, and audit telemetry; owned live-service operations including incident handling, escalation flows, backups, and continuous optimisation; ran architecture workshops with IT leadership and service owners to align AI behaviour with institutional risk appetite.
AI Program Manager – LLM Systems at Google
May 1, 2024 - May 1, 2025
Senior post-sale technical role deploying LLM-powered systems within globally scaled, policy-constrained environments; supported rollout of production LLM systems from pilot to full deployment across multiple regions; designed evaluation loops and telemetry pipelines tracking output accuracy, behavioural drift, and operational impact; partnered with engineering, product, research, policy, and legal teams to harden experimental capabilities into reliable enterprise features; treated prompts, tools, evaluation criteria, and policies as versioned artefacts enabling controlled iteration.
Conversational AI Engineer – Public Sector (HMRC) at Microsoft
December 1, 2022 - April 1, 2024
Delivered large-scale conversational AI and automation systems in a highly regulated public-sector environment; conducted technical discovery with senior stakeholders to map operational constraints and service boundaries; designed policy-governed AI behaviours, fallback strategies, agent logic, and secure backend integrations; built telemetry-driven feedback loops linking AI performance to service outcomes.
Conversation Designer at Avaya
June 1, 2021 - September 1, 2022
Designed and optimised AI-driven automation and qualification assistants for telecoms and financial services clients; built API-integrated conversational workflows enabling real-time routing and CRM hand-off; improved performance via log analysis, architectural simplification, and flow optimisation.
AI Service Designer at Versus Arthritis
November 1, 2020 - June 1, 2021
Owned the charity’s national virtual assistant supporting digital triage and accessible user journeys; implemented analytics-driven optimisation and safeguards for vulnerable users.

Education

MA Computational Design at Goldsmiths, University of London
January 11, 2030 - January 22, 2026
MA Computational Design at Goldsmiths, University of London
January 11, 2030 - January 22, 2026

Qualifications

Microsoft Certified — Azure AI Fundamentals
January 11, 2030 - January 22, 2026
DeepLearning.AI — Neural Networks & Deep Learning
January 11, 2030 - January 22, 2026
IBM RAG and Agentic AI
January 11, 2030 - January 22, 2026
Azure AI Fundamentals
January 11, 2030 - January 22, 2026
Neural Networks & Deep Learning (DeepLearning.AI)
January 11, 2030 - January 22, 2026
IBM RAG and Agentic AI
January 11, 2030 - January 22, 2026

Industry Experience

Government, Education, Professional Services, Software & Internet, Non-Profit Organization