Location: Bristol / Hybrid (2x on-site)
Type: Permanent, Full-time
SR2 is partnering with an exciting digital health technology company that works with pharmaceutical, biotech and healthcare organisations to build AI and data-driven solutions addressing real-world challenges.
We're looking for a Forward Deployed Engineer who combines strong software engineering with hands-on experience building modern AI and agentic applications.
This is a builder-first role working closely with clients and product teams, take ambiguous problems, turn them into something concrete and then build, deploy and own the solution end-to-end.
What you'll be doing
- Work directly with business, technical and product stakeholders to understand complex problems and determine what should be built.
- Rapidly turn ideas into working prototypes and production applications.
- Build full-stack applications, APIs, AI agents and multi-step workflows.
- Develop primarily with Python and/or TypeScript.
- Build agentic applications using technologies such as LangGraph, AutoGen, Claude Agent SDK and OpenAI Assistants.
- Integrate Claude, GPT, Gemini and open-weight models with external tools, data and systems.
- Work with MCP (Model Context Protocol) and custom connectors.
- Build RAG and retrieval pipelines using vector databases such as Pinecone, Chroma, Weaviate and pgvector.
- Develop evaluation frameworks to measure AI accuracy, reliability, latency and cost.
- Use modern AI development tools including Claude Code, Cursor, GitHub Copilot and Codex.
- Deploy and own applications in production across AWS, Azure, Cloudflare or Vercel.
- Work with Docker, Kubernetes, CI/CD, testing, security and observability.
- Demo working software directly to stakeholders and iterate quickly based on feedback.
What we're looking for
- 3+ years' relevant experience building production applications using AI / agentic development approaches.
- Strong commercial experience with Python and/or TypeScript.
- Hands-on experience building AI agents, rather than only working with prompted LLMs.
- Experience connecting models to tools and creating multi-step agentic workflows.
- Strong understanding of modern LLMs and Generative AI.
- Experience with RAG, vector databases and retrieval pipelines.
- Practical experience building and using AI evaluation harnesses.
- Strong software engineering fundamentals including OOP, SOLID, clean architecture and microservices.
- Experience deploying applications into cloud environments.
- Understanding of TDD, CI/CD, security, scalability and observability.
- Confidence working directly with stakeholders and turning ambiguous requirements into working software.
- Evidence of things you've recently built - whether commercially, through GitHub, open-source projects, side projects or your own products.
- A degree in Computer Science, Machine Learning or a related technical discipline.
Nice to have
- Healthcare or life-sciences experience.
- MLOps and model-serving experience.
- Data pipeline experience with technologies such as Spark, Airflow, Beam or Glue.
- Public writing, talks or contributions around AI engineering.
- Relevant AWS or cloud certifications.
Why consider it?
- Build at the forefront of AI and agentic software engineering.
- Take genuine ownership from problem discovery through to production.
- Work directly with clients rather than being several layers removed from the problem.
- Build technology tackling meaningful challenges across healthcare and life sciences.
- Join an organisation investing in its growing UK engineering capability.
- Work alongside experienced international engineering, product and technology teams.
- Competitive compensation and opportunities for continued development.