AI Engineer · Available for work
Apps and agents,built to hold upin production.
8+ years of engineering depth. 18+ months building production-grade AI projects — Claude, MCP, evals, agents. Shipping open-source demos, writing about what breaks in production, and pairing with teams who want AI features done right.
Past work: Proconvey (legal-tech) · ThePRSB (healthcare) · TNBC Support (healthcare) · Anthony MacQuillan (Harley Street)·Based in Mumbai — async-first
Selected work
Eight years of shipping
for real users.
UK healthcare orgs, UK legal-tech (Proconvey), luxury e-commerce, and B2B SaaS. The work spans WordPress, custom Next.js apps, Shopify, and React. The common thread: production code that holds up under real users.
Proconvey
ProConvey is an all-in-one SaaS conveyancing software solution. Custom web application development with React and Next.js, cloud-based platform streamlining onboarding for UK conveyancers and estate agents.
Anthony MacQuillan
Premium healthcare website development for world-class plastic surgeon. Custom WordPress theme with SEO optimization, patient education resources, and WCAG 2.1 AA accessibility compliance.
UrbanZen
Shopify custom theme development for luxury lifestyle brand. Premium e-commerce website featuring womenswear, jewelry, bags, belts, scarves, home accessories with conversion-optimized shopping experience.
ThePRSB
ThePRSB develop evidence based standards for digital health and social care records. Find out more New Quality Partner Leapmind-iStaffRota is our latest Quality Partner to achieve conformance against our standards.
TNBC Support
TNBC Support has been developed and funded by Gilead Sciences Ltd for people living with TNBC and their carers in the UK and Ireland.
InnerWings
Discover free school programmes designed to build confidence and resilience in children, promoting self-worth and acceptance.
What clients say
In theirown words.
Robin is my hero. I was struggling with the ex web developer who tries to charge me unreasonable amount of money. Fortunately, I connected with Robin and he helped me in every possible way. I am very impressed. Due to the lack of knowledge of IT, Robin must have been tired to explain every single detail that I had no ideas of. But now I do understand some of them! And I guarantee that no one would regret working with him. It’s privilege! I was so lucky!!! Thank you Robin for your expertise and professionalism. I will work with him again 100%. Thank you so much. From London.
Excellent is the only word I can find to describe his skill set... He did everything I wanted at a very fast speed and went beyond my expectations!!! I was so impress I decided to double the rate I initially had for the project. That is how satisfied I am with his service. Thank you Robin for accepting to work with me and make my day!
How I work
Boring on process,interesting on code.
Async by default.
No daily standups. You get a written update at the end of each working day — what shipped, what's blocking, what's next. If we need to talk, we hop on a 30-min call.
Fixed scope, fixed price.
I don't sell hours. Every engagement has a defined deliverable. If it takes longer than estimated, that's on me.
Code in your repo from day one.
I push to your repo from commit one. There's no “handoff phase” — you're handed off the entire time.
Reachable across timezones.
Mumbai-based, async-first. Reasonable overlap with EU and US-East working hours. Same-day Slack response on workdays.
About
Solo, senior,shipping in your repofrom day one.
I’m Robin. 8+ years building SaaS products and websites for startups and established companies — UK healthcare orgs, a UK legal-tech SaaS (Proconvey), a luxury e-commerce brand, a Harley Street surgeon’s site, dozens of others.
The last 18+ months I’ve gone deep on AI engineering — Claude, the Anthropic SDK, MCP, agents, eval harnesses, and the unglamorous parts (cost monitoring, prompt versioning, fallback strategies) that decide whether an AI feature actually holds up in production.
I work solo. No agency, no junior devs, no offshore team you didn’t agree to. The person you talk to is the person writing the code.
Production-grade by default
Cost monitoring, prompt versioning, eval harnesses, fallback strategies — the unglamorous parts that decide whether an LLM feature actually holds up in production.
Apps and agents depth
18+ months building production-grade AI projects — apps, agents, MCP servers, eval harnesses. Plus 8+ years of full-stack engineering that the AI work sits on top of.
Build in public
Currently shipping open-source demos, writing what I learn, and pairing with teams who want AI features done right. Async-first. Code in your repo from commit one.
Get the AI Engineer dispatch.
New long-form post + the build I shipped that week. No filler, no roundups.
Get in touch
Working on somethingAI-shaped?
Intro calls are 20 minutes, free, and only useful if I think I can actually help. If I can’t, I’ll tell you.