> Markdown version of [/jobs/ext/3268358-lead-ai-llm-developer-team-lead](https://www.wearedevelopers.com/jobs/ext/3268358-lead-ai-llm-developer-team-lead). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Lead AI & LLM Developer Team Lead - **Company:** CMe Media/CMe Automotive - **Location:** Lee-on-the-Solent, UK (Remote available) - **Experience:** Expert - **Salary:** £60,000.0 - £90,000.0 - **Contract:** Permanent contract - **Skills:** JavaScript (Programming Language), Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, User Authentication, Automation of Tests, Microsoft Azure, Business Systems, Cloud Computing, Cyber Security, Databases, Continuous Integration, Data Governance, Information Leak Prevention, Monitoring of Systems, Python (Programming Language), Key Management, Regression Testing, Software Safety, Search Technologies, Software Deployment, TypeScript, Data Logging, Google Cloud, Retrieval-Augmented Generation, Large Language Models, Backend, Git, Integration Frameworks, Non-relational Database, Api Design, Software Version Control, Data Pipelines - **Published:** September 11, 2026 - **Apply:** https://www.indeed.com/viewjob?jk=d8d55ef5dab3a959 ## About the Role Experience using AI through consumer interfaces alone will not be sufficient. You must understand how to engineer LLMs into controlled, secure and commercially dependable products. Wider technical experience You will ideally have substantial experience across several of the following: * Python and modern software-engineering practices * TypeScript, JavaScript or relevant full-stack technologies * API architecture and third-party integrations * AWS, Microsoft Azure or Google Cloud * Relational and non-relational databases * Secure and scalable application architecture * Git and collaborative development workflows * Automated testing and CI/CD * Logging, monitoring and application observability * Authentication, permissions and secrets management * Data governance, GDPR and cybersecurity * Production deployment and ongoing application support Experience with LangChain, LlamaIndex, LangGraph or comparable frameworks would be useful, although sound engineering judgement is more important than dependence on one framework. Proven delivery is essential This is a senior appointment. Applicants must demonstrate successful delivery of AI-powered or technically complex products and management of a team. You should be able to evidence: * LLM or AI applications you personally designed and built * Products that progressed beyond experimentation into live operational or commercial use * Your individual technical contribution and level of ownership * The architecture, models and infrastructure you selected * How you managed accuracy, security, safety, performance and cost * How you addressed unreliable model behaviour and technical failure * Continued product improvement following testing and user feedback * Successful collaboration with commercial and non-technical stakeholders * Measurable outcomes such as adoption, revenue, efficiency, cost reduction or customer value * Experience leading developers, suppliers or multidisciplinary technical teams We do not expect candidates to have trained a foundation model from the ground up. We do expect extensive experience building valuable applications around LLMs and related AI technologies. ## Description We are now making a significant investment in our internal AI capability and are looking for an exceptional Lead AI & LLM Developer to establish and lead our new development function. The opportunity Working directly with our CEO, senior leadership team and specialists across the group, you will take new AI products from discovery and technical validation through to live deployment, adoption and continued commercial development. Initially, you will be a highly hands-on technical lead, taking ownership of our architecture, development roadmap and first core products. As the function grows, you will help recruit, mentor and lead a wider internal AI team. This is not a maintenance position, a purely strategic role or an opportunity focused on producing isolated proofs of concept. You will combine technical leadership with hands-on development and will be accountable for turning viable ideas into dependable products that people can use. What you will be responsible for * Defining our technical vision, architecture and AI development roadmap * Translating commercial opportunities and operational challenges into clear product and technical requirements * Leading products from discovery and prototyping through to production deployment * Building minimum viable products and scalable, production-ready applications * Designing applications powered by large language models * Working extensively with Anthropic Claude, OpenAI, Google Gemini and other suitable models * Selecting models based on quality, reasoning ability, speed, security, context capacity and cost * Designing advanced system prompts, context strategies and reusable prompt architecture * Building structured outputs, function calling, tool use and agentic workflows * Developing retrieval-augmented generation systems, embeddings, vector databases and governed knowledge bases * Connecting AI applications to business systems, websites, databases, CRM platforms and third-party services * Establishing effective guardrails, fallback behaviour and human-review processes * Protecting applications against prompt injection, data leakage, inappropriate tool use and unsafe outputs * Creating evaluation frameworks for accuracy, relevance, consistency, hallucinations, bias and task completion * Building automated regression testing so changes to prompts or models can be measured safely * Monitoring deployed systems for quality, reliability, latency, token consumption and cost * Determining when prompting, RAG, model routing, fine-tuning or a conventional software solution is most appropriate * Exploring multimodal AI involving text, images, documents, audio and video * Supporting the development of voice-AI applications where relevant * Designing secure APIs, back-end services, data pipelines and cloud infrastructure * Managing deployments, version control, technical documentation and system observability * Applying GDPR, security and responsible-AI principles throughout the development lifecycle * Protecting company intellectual property, code, data, prompts and product knowledge * Leading controlled testing with internal teams, customers and prospective users * Measuring adoption, business value and product performance following launch * Setting realistic budgets, resources, milestones and delivery timescales * Reporting progress, risks, dependencies and decisions clearly to the leadership team * Recruiting, mentoring and leading developers and AI specialists * Establishing coding, testing, documentation and responsible-AI standards for the team Essential LLM expertise You must have extensive hands-on experience designing and deploying applications powered by large language models. This should include: * A strong understanding of tokens, context windows, inference settings and model limitations * Advanced system prompting and context engineering * Anthropic Claude and the Anthropic API * OpenAI models and APIs * Google Gemini or other leading foundation models * Structured outputs, function calling and tool use * Agentic and multi-stage LLM workflows * Model Context Protocol or comparable tool-connection methods * Retrieval-augmented generation * Embeddings, semantic search and vector databases * LLM evaluation, benchmarking and observability * Guardrails and application-level AI safety * Prompt-injection and data-leakage protection * Prompt caching, token optimisation and API-cost management * Model routing and model comparison * Understanding when fine-tuning is appropriate * Monitoring and improving live LLM applications after deployment, * What you designed and built * Whether it reached live deployment * Your personal responsibilities and contribution * The models, platforms and technologies used * Your approach to prompting, RAG, testing, guardrails and evaluation * The timescale and team structure * Significant technical challenges and how you resolved them * Measurable commercial, customer or operational results * A product, demonstration, case-study or repository link where confidentiality permits Shortlisted applicants may be asked to complete a relevant technical assessment and discuss their previous projects in detail. Pay: £60,000.00-£90,000.00 per year Benefits: * Additional leave * Casual dress * Company events * Company pension * Free parking * On-site parking * Sick pay * Work from home