About the role
Our AI & Automation practice helps clients turn ideas into dependable products. You will build features end to end, from prototype to production, and help us decide where AI genuinely adds value.
What you will do
- Build LLM-based features such as chat assistants, retrieval (RAG), summarisation, and extraction
- Design prompts, tool-calling flows, and evaluation sets to measure quality
- Build backend services and APIs that integrate models into web and mobile apps
- Monitor cost, latency, and accuracy, and improve them over time
- Work with clients and product teams to scope AI use cases realistically
- Document designs and share what you learn with the team
What we are looking for
- 2+ years of professional software or ML engineering experience
- Strong Python; comfortable with TypeScript/Node.js is a plus
- Experience building with LLM APIs (Anthropic, OpenAI, or open-source models)
- Understanding of embeddings, vector search, and retrieval pipelines
- Experience building and deploying REST APIs and working with databases
- Good grasp of Git, testing, and writing maintainable code
Nice to have
- Experience with LangChain, LlamaIndex, or similar frameworks
- Cloud deployment experience (AWS, GCP, or Azure) and Docker
- Classical ML or fine-tuning experience
- Prior client-facing or consulting work
What we offer
- Remote-first, flexible working hours
- Ownership of features from prototype to production
- Learning budget and access to the latest AI tooling
- Work across industries on varied, real problems