I'm a software engineer specialising in AI engineering

AI Engineer · Co-founder, Nur Opus · Previously V7 Labs · MSc Artificial Intelligence

I develop performant and efficient Large Language Model (LLM) applications through observability, evaluation pipelines, and context engineering, all built on strong backend and infrastructure engineering foundations. I'm currently expanding into LLM post-training as an active area of learning and research.

GitHub ·CV · john1091w@gmail.com

What I've done

Throughout my career, I've sought increasingly technical roles. Starting in technical support at Verkada and V7 Labs, I began making contributions to V7's public SDK, darwin-py. This earned me a full-time development position at V7, where I became darwin-py's sole author and maintainer, and owned the backend systems responsible for 2D & 3D medical imaging data (DICOM, NIfTI) for their labelling platform, Darwin. Along the way I refactored darwin-py's core I/O layer for concurrency, delivering an up-to-8× throughput improvement.

I then co-founded Nur Opus, where I led the development, delivery, and maintenance of bespoke LLM applications and evaluation pipelines across multiple verticals.

Alongside this, I built Infinite Bazaar as part of a small team: an experiment in agentic machine economies, where AI agents establish verified identities, publish paid services, and trade with one another autonomously. We took 3rd prize at Coinbase's "Agents in Action" hackathon, and I presented the project at the AWS Builder Loft in San Francisco.

What I'm doing now

I'm building Orient: a self-hostable LLM engineering platform, inspired by problems that recurred across nearly every Nur Opus client engagement, best summed up as: "How do I optimise my LLM agent, and keep it optimised over time?" With Orient, you instrument your application with the Python SDK, and production data streams in as traces, which are continually evaluated by reusable deterministic and calibrated LLM-judge evaluators. Failing traces are curated into regression datasets, then Orient tests different context strategies and models to find optimal agent configurations.

Alongside Orient, I'm learning LLM post-training from scratch. Recent rapid improvements in both the cost and performance of open-source LLMs and post-training methods, particularly reinforcement learning (RL), point to a future of continually evaluated, highly-specialised fine-tuned small language models (SLMs) as the optimal way to build with LLMs in most cases. For that reason I'm learning how to engineer models using SFT, DPO, LoRA/QLoRA, RLHF, RLVR, and synthetic data pipelines, and am keen to contribute solutions and research in these areas.

Writing

I write about all things LLM: engineering, training, industry and economic trends.