PROJECT OVERVIEW
Our Client is building AI-powered capabilities — real-time transcription, automated documentation — that help hearing care professionals spend less time on admin and more time with patients.
As a Senior AI/LLM Engineer, you will build the LLM capabilities that go into our Client products and into our internal platform. Our client develops enterprise software for audiology clinic chains and hospitals. AI has moved out of pilots and into the product roadmap, so this work ships to real users in a regulated,patient-data environment. This is a role for engineers who take a feature from first prototype to something that runs reliably in production.
Tech environment: C# / .NET 8.0, Azure Services (Azure SQL, AI Search, Service Bus, App Insights), Azure AI Foundry, Docker, Kubernetes, plus growing use of Python for AI tooling and experimentation. We build AI-first with Claude / Claude Code.
IN THIS ROLE, YOU WILL
Build and ship LLM features: retrieval (RAG), agents, tool use, and structured output, integrated into our .NET services.
Own quality: build evaluation sets, measure before and after every change, and catch regressions before customers do.
Run it in production: latency, cost per request, caching, fallbacks, monitoring, and alerting.
Build guardrails: prompt-injection defence, PII handling, output validation, and audit trails.
Build shared building blocks that other product teams reuse, so the same problem is not solved five times.
Work with product teams and architects to choose the right tool. Sometimes a simple rule beats a model. Say so when it does.
Work AI-first: use Claude / Claude Code in daily development to design, build, and test faster.
Participate actively in a remote scrum team: sprint ceremonies, PR reviews, and knowledge sharing.
IF YOU ARE
5+ years building production software, with strong C# and modern .NET (.NET Core / .NET 6+);
1-2+ years building LLM features that reached production and real users;
Retrieval done properly: chunking, embeddings, hybrid search, reranking, and honest measurement of result quality;
Agents and tool use: function calling, MCP or a similar tool protocol, multi-step flows with error handling;
Evaluation discipline: you have built eval sets and used them to decide. You can explain how you knew a change was an improvement;
Cloud experience (Azure preferred) and solid engineering fundamentals (clean design, testing, CI/CD);
Cost and latency awareness: you know what your features cost per request, and why;
Hands-on experience developing with AI coding assistants (Claude / Claude Code, Copilot, or similar). Our Client builds AI-first, so this is part of daily work.
Comfort working autonomously in a remote, async-friendly team;
Strong written and spoken English (B2+);
Pragmatism: in the interview we will ask for a case where you decided that a simple rule, or a small classic model, was the better answer than an LLM.
NICE TO HAVE
Python for AI tooling, evaluation, and prototyping;
Running open-source models on your own infrastructure (containers, GPU or CPU inference);
Applied machine learning: forecasting, prediction, optimisation;
Azure AI Foundry, Azure AI Search, Azure ML;
Experience working in regulated domains or with sensitive data (GDPR, ISO 27001 / ISO 42001).
AS AN OPINOV8R, YOU WILL HAVE
Digital-First Approach: Great talent knows no borders! You can work from wherever you are — we hire and collaborate with professionals worldwide.
Remote Work Model: Balance your professional and personal life with our flexible working conditions, empowering you to deliver your best from anywhere.
Exciting Projects: Dive into impactful projects across industries that challenge and spark creativity.
Boost Your Expertise: Grow your career with continuous learning, development opportunities, and hands-on experience.
Join the Best Team Ever: Collaborate with our diverse and cross-cultural team of passionate technologists and creative thinkers.
H
