Lead AI Engineer
Uses AI-assisted development tools like Claude Code, GitHub Copilot and Cursor in structured workflows; explicitly not promoting informal "vibe coding."
About the Role
Lead AI Engineer to architect and deliver production-grade Generative AI and agentic systems, driving end-to-end model selection, orchestration, and scalable backend implementation. Individual-contributor technical leader who partners with product and ML teams to turn research into production-ready healthcare solutions.
Job Description
Role
We are hiring a Lead AI Engineer to design, build and optimise production-grade Generative AI and agentic applications for healthcare clients. This individual-contributor leadership role owns architecture, orchestration, model selection, RAG/retrieval pipelines, backend microservices and cloud-native deployments to move AI research into secure, scalable production systems.
Key Responsibilities
- Architect and implement Generative AI and agentic systems using orchestration frameworks and LLMs (GPT, Claude, Gemini, self-hosted models).
- Implement Retrieval-Augmented Generation (RAG) pipelines with vector databases and search engines (Pinecone, ChromaDB, Weaviate, pgvector, ElasticSearch, Solr) and TF/IDF / BM25 and similarity search techniques.
- Build multi-modal workflows (text, image, voice, video) and design prompt/context engineering frameworks to improve accuracy, repeatability, cost and latency.
- Implement guardrails, observability, monitoring and model fine-tuning for domain-specific use cases.
- Develop microservices and modular backends (Python, JavaScript, Java) following DDD, SOLID, OOP and clean architecture; integrate databases (relational, document, key-value, graph) and event-driven systems (Kafka/MSK, SQS).
- Deploy cloud-native systems on AWS/GCP/Azure using containerisation, orchestration (Docker, Kubernetes) or serverless approaches; implement CI/CD pipelines (GitHub Actions, Jenkins).
- Use AI-assisted development tools (Claude Code, GitHub Copilot, Codex, Roo Code, Cursor) as part of structured developer workflows while maintaining code quality.
- Provide technical mentorship, lead POCs and innovation sprints, and collaborate with Product, Design and ML teams.
Requirements
- 7–12 years total software development experience with at least 3 years in AI/ML systems engineering or Generative AI.
- Proven experience building and deploying GenAI/LLM systems to production; deep understanding of LLM behaviour, context engineering and prompt optimisation.
- Hands-on experience with Python or JavaScript (or Java), OOP, SOLID principles, 12-factor apps, microservice architecture, and scalable system design.
- Experience with vector databases, retrieval pipelines and RAG implementations.
- Cloud-native deployment experience in AWS/GCP/Azure; familiarity with Docker, Kubernetes and CI/CD (GitHub Actions, Jenkins).
- Strong engineering practices: TDD, clean code, security-first design (secrets management, SAST/DAST), observability (logging, metrics, tracing), and performance/cost optimisation.
- Demonstrable use of AI-assisted development tools and structured workflows.
- Bachelor’s or Master’s degree in Computer Science, Machine Learning, or related technical discipline.
Bonus / Nice-to-have
- Experience with MLOps and model serving/monitoring tools (BentoML, MLflow, Vertex AI, AWS SageMaker).
- Experience building streaming and batch data pipelines (Spark, Airflow, Beam).
- Mobile or front-end web development experience.
Location & Employment
- Location: Bristol
- Working model: Hybrid
- Employment type: Full-time
What the company offers
- Competitive compensation, career growth opportunities, supportive people-first culture, and work-life balance.