About the Role
Bring LLM-powered features to life inside a real, shipping edtech product — practical delivery work that turns AI capability into something users actually touch, not research for its own sake.
Responsibilities
- Integrate LLM APIs (OpenAI, Anthropic, or similar) into product features
- Build lightweight RAG pipelines using embeddings and vector search
- Prototype and productionise AI-powered features (chat, summarisation, search, classification)
- Work with vector databases (pgvector, Pinecone, Qdrant, or similar)
- Advise the team on realistic AI use cases, weighing cost, latency and reliability
Required
- 2–4 years software engineering experience, with hands-on LLM/GenAI integration experience
- Strong Python skills
- Practical experience with at least one LLM provider's API
- Understanding of the cost/latency/reliability tradeoffs of AI features
- Comfortable explaining AI limitations to non-technical stakeholders
Additional Information
- Nice to have: LangChain, LlamaIndex or similar orchestration frameworks
- Delivery-focused role — a data science background is not required
Contract and Payment Terms
- Length: 1–4 months initially, frequently extended
- Engagement: B2B contract, full-time or part-time by arrangement
- Rate: €35–45/hour (or £450–500/day equivalent)
About Cognexis
Cognexis is a specialised talent partner for growing technical teams, matching engineers to roles in AI, data, software engineering, cybersecurity and cloud infrastructure.
You'll be part of a network of tech companies, working alongside industry-leading talent to shape the future of AI.