I was the first developer hired on ClassCharts, the behaviour and parent-communication platform used by thousands of UK schools, and stayed eight years while it grew to more than ten million pupils, parents and teachers. Since 2024 I have shipped LLM features to production, most recently usage metering and memory for an AI tutor used by millions of students.
Open to a long-term role, employed or on a B2B contract. What I'm looking for →
"Borut delivered immediate value after joining our team." Selected organisations I've worked with
Direct long-term engagements with Edukey and TES Global; the rest delivered as the engineer on projects contracted through partner agencies.
Most recent first, back to my eight years on ClassCharts.
An AI tutoring and exam-preparation platform used by millions of secondary-school students across web, iOS and Android. I replaced message-count entitlements with cost-based usage metering across every plan tier, built the AI tutor's memory pipeline, and added credit top-ups with the usage administration interface.
Took over an agency-built investment-intelligence platform covering 20+ global markets. Worked hands-on across the application, AI layer and infrastructure, alongside colleagues in frontend, backend/data APIs and design. The company wound down in March 2026.
Backend engineer on a smart-city programme where several vendor teams built five city domains at the same time. I designed and built 20+ microservices on Kubernetes and the event-driven layer from the IoT gateways inward, on Kafka and Cassandra. The C4 architecture models I made from the specifications became the reference the vendor teams built against.
Joined as the first developer alongside the CTO and stayed through the growth of ClassCharts from hundreds of thousands of users into a platform serving more than ten million pupils, parents and teachers across the UK education system, and through its acquisition by TES Global. The scope moved with it: building the product, then rebuilding the web app from jQuery to React in place, then taking mobile from an Android-only native app to React Native on both platforms, then the infrastructure through Rackspace, GCP and AWS, then onboarding the teams that arrived with the acquisition.
Four systems I built around language models, two for clients and two of my own. Each one links to a diagram of how it works and the decisions behind it.
A cheap model makes the first cut and a stronger one only runs where the call is hard. One provider registry covers OpenAI, Azure OpenAI and Perplexity, and the earnings-call summariser moved from OpenAI to Gemini in production.
AI tutoring platform · clientUsage is metered by what each request costs in tokens, checked before the model call and charged only once it succeeds. The tutor's memory is extracted from conversations in the background and cleaned up nightly.
Metis · my own platformThe pipeline takes in around 100,000 articles a day and stores their embeddings in Qdrant. Natural-language search finds related articles by meaning, and an LLM agent pulls related news by similarity before it makes a call.
Guestavo · my own productAn MCP server lets an operator manage menus, bookings, shifts and reports from an AI client. Every change an agent makes is logged with its before and after state and can be undone, and API keys are scoped per organisation, property and action.
I also build with coding agents every day, Claude Code and Codex now, inside tooling I wrote: versioned workflows with a gate and a model tier per phase, and MCP servers that give agents real project state. Nothing public ships without a human reading it first. Read how it works →
" I worked with Borut for 8 years, he was our longest serving developer and he was an excellent person to work with. Borut always feels & displays a high level of responsibility to the project and the team and brought immense value to what we were trying to achieve, he understood our vision & grew with our codebase to become a hugely valued developer who you could rely on & would always deliver. Time keeping, attention to detail & working with others were never a problem. Borut worked on each of our products, working with different team members, platforms and codebase & responsibilities. I have zero hesitation in recommending Borut as he is an intelligent & hard working individual with a good sense of humour and liked by the rest of the team - he was a huge asset! " " Borut delivered immediate value after joining our team. He brought clarity to complex problems, unlocked efficiency, and significantly increased throughput. He quickly identified mission-critical technical debt and resolved it on schedule. Borut communicates clearly with both technical and non-technical stakeholders and consistently connects technical concepts to practical business goals. His experience enables him to leverage AI to accelerate delivery without compromising quality. We were fortunate to have him on board and would gladly collaborate with him again or recommend him for any project. " Senior or AI engineer roles, or a technical lead seat where I still write code. EU employment or a long-term B2B contract.
Send the role description with your stack and timing.
My client work has been contracted B2B through Corco Labs, because most of my clients were abroad and could not employ me in Slovenia.
Senior Software Engineer, AI & LLM Systems