I build AI/ML systems that ship, from London: retrieval and ranking, agents and evaluation. Today that is the shopping assistant at Rezolve Ai; before that, the multi-agent platform at Writer.
I got here through a journey, not a straight line: founder, hands-on CTO, team lead. That is why unclear needs, missing pieces and pressure don't surprise me. I see problems early, learn fast and stay calm while solving them.

19 years building software: founding companies, leading teams and switching stacks. This is what I carry into every AI project, together with a taste for quality and an eye for the details that make it feel finished.
I have run my own companies, so I think about customers, cost and the team, not just the code. At DIGIEGGS I trained a team from junior level and delivered 20+ projects for 15 clients.
Proof: DIGIEGGS
At Writer I led a team of 4 on Agent Deployment, and got security, DevOps and customer teams behind one design.
Proof: Writer Agent Deployment
New stack, new domain, same calm: I switch context without losing speed. I went from embedded software to SAP consulting, then to web, mobile and now AI/ML.
Proof: Experience
I question the default before I follow it. Social apps share by default, so at Logg we made privacy the default instead. Apple made it App of the Week and Product Hunt made it App of the Day.
Proof: Logg
I use AI agents every day, but I own what ships. User stories and behavioural checks tell them how the code must behave under load and across tangled dependencies, so they work like clones of me. I review their output like a new hire's, and evals and tests, not a confident answer, decide when it is done. That is how broken replies went from about 7% to zero.
Proof: Rezolve Ai
When the obvious fix is too slow or too costly, I find another way in, with a bias toward execution. A cloud-only SaaS became an on-premise product in two weeks because I made its data layer point at another database instead of rebuilding it.
Proof: Upsolve on-prem
I build what users will pay for, not what's fun to build. At Commented, customers and sales data showed us where the value was, so we moved from a general commenting tool to collaboration between software teams and their clients. Since launch, 800+ teams have left 56,000+ comments on it.
Proof: Commented
Conversational AI, measured
Retrieval and ranking, intent matching, attribute extraction and vision models for an AI shopping assistant, with a knowledge layer merchants author themselves. Evaluations decide what ships: first responses got about 30% faster.
Proof: Rezolve AiMulti-tenant agent execution
Per-tenant sandboxes on Cloudflare Containers and Durable Objects, with MCP OAuth integrations for tools.
Proof: Writer Agent DeploymentSecrets and security hardening
Decrypt-on-demand encrypted environment variables, ClamAV malware scanning, Redis rate limiting and a DynamoDB partition key strategy.
Proof: Writer Agent DeploymentCloud to on-premise
Containerised a cloud SaaS for on-premise deployment, with a dynamic data layer, migrations and SQL import and export.
Proof: Upsolve on-premServerless on AWS
Lambda, GraphQL and CloudFront behind SDKs, a browser widget and an admin panel.
Proof: CommentedAWS Certified Solutions Architect, Associate
Amazon Web Services, valid to 2029
Earlier: SAP and Microsoft certifications
SAP Certified Application Associate, CRM (2013); Microsoft MCTS 70-562 and MCP 70-536 (.NET); Bilge Adam Database and Software Specialist (2010)
BSc Computer Engineering
Dokuz Eylül University, Izmir
A journey, not a ladder.
Started in embedded software, then became an SAP certified consultant at Astron, Yaşar Holding's IT company, on CRM and project portfolio systems.
Founded DIGIEGGS: 15 clients, 20+ projects and our own products for pharma, events and IoT.
Co-founded Logg and Commented, and led engineering at Karshare and Bermudair Airlines as a founding engineer.
Led a team of 4 on Agent Deployment, the multi-agent platform inside Writer's Agent Builder. Now I own the AI/ML behind Rezolve Ai's shopping assistant.

2026Live site
20252026
20242025Live site
2019202020212022
2024
20232024Live site
20172018Live site
20142015201620172018The CV and project write-ups have the details.