What you'll do
- Design, develop and optimise GenAI powered search and conversational chatbot experiences that integrate seamlessly into scalable mobile and TV applications used by end users.
- Build retrieval augmented generation (RAG) pipelines combining LLMs with structured and unstructured data.
- Optimise relevance, latency, and response quality for interactive UI components.
- Evaluate and improve models using real world feedback, analytics and experimentation.
- Collaborate closely with frontend, product and UX teams to embed AI components into user facing applications.
- Contribute to system architecture, model selection and deployment strategies.
- Provide technical guidance and mentorship to junior members of the engineering team.
- Participate in Scrum/agile processes.
- Participate in on call support with the rest of the team.
What you'll bring
- Extensive experience with traditional ML systems and GenAI (LLMs, agent frameworks), including proven delivery of GenAI powered search or chatbot solutions in production.
- Working experience and in depth understanding of Large Language Models (LLMs), vector databases and semantic search, and retrieval augmented generation (RAG).
- Extensive programming expertise, primarily in Python, delivering ML and GenAI solutions with a language agnostic mindset.
- Familiarity with cloud services, e.g. AWS Lambda best practices.
- Strong team player and confident communicator with experience as a tech lead and individual contributor in agile, fast paced environments.
Inclusion & how you'll work
We are a Disability Confident Employer, and welcome and encourage applications from all candidates. We will look to ensure a fair and consistent experience for all, and will make reasonable adjustments to support you where appropriate. Please flag any adjustments you need to your recruiter as early as you can.
If your application is successful, you will be asked to complete a criminal record check. Depending on the role and any convictions, we may have to withdraw the offer.