The ad says“Fluency with the modern LLM/agent toolkit — model APIs, prompting, tool use, RAG, and the patterns this fast-moving ecosystem is converging on (MCP, agent frameworks, evals)”
The ad says“Experience in drug discovery, biology, or another life science domain”
The ad says“Interest in or experience with biotech / techbio and its impact on patient outcomes”
The ad says“Experience in drug discovery, biology, or another life science domain”
The ad says“Fluency with the modern LLM/agent toolkit — model APIs, prompting, tool use, RAG, and the patterns this fast-moving ecosystem is converging on (MCP, agent frameworks, evals)”
The ad says“Experience building evaluation harnesses or testing strategies for LLM systems”
The ad says“Familiarity with knowledge graphs or reasoning over structured or heterogeneous data”
The ad says“Experience in drug discovery, biology, or another life science domain”
The ad says“You’ve built and shipped LLM-agentic systems that deliver real value — agents that use tools, orchestrate multi-step workflows and behave reliably in production”
The ad says“Fluency with the modern LLM/agent toolkit — model APIs, prompting, tool use, RAG, and the patterns this fast-moving ecosystem is converging on (MCP, agent frameworks, evals)”
The ad says“Fluency with the modern LLM/agent toolkit — model APIs, prompting, tool use, RAG, and the patterns this fast-moving ecosystem is converging on (MCP, agent frameworks, evals)”
The ad says“Fluency with the modern LLM/agent toolkit — model APIs, prompting, tool use, RAG, and the patterns this fast-moving ecosystem is converging on (MCP, agent frameworks, evals)”
The ad says“You have at least 2 years of software engineer or ML engineer working experience. And you have strong software engineering fundamentals — you write clear, tested, maintainable Python code that others can build on”
The ad says“Fluency with the modern LLM/agent toolkit — model APIs, prompting, tool use, RAG, and the patterns this fast-moving ecosystem is converging on (MCP, agent frameworks, evals)”
The ad says“Familiarity with knowledge graphs or reasoning over structured or heterogeneous data”
The ad says“Interest in or experience with biotech / techbio and its impact on patient outcomes”
The ad says“Experience building evaluation harnesses or testing strategies for LLM systems”
The ad says“Fluency with the modern LLM/agent toolkit — model APIs, prompting, tool use, RAG, and the patterns this fast-moving ecosystem is converging on (MCP, agent frameworks, evals)”
Healx is looking for an Agentic AI Engineer to build LLM-agentic workflows that power our drug discovery platform
Reporting to our Director of Tech Strategy, you’ll design and build agents that solve real drug discovery problems
Working closely with scientists across the company, you’ll understand the questions that matter most to their work, then design and refine agents that reason over our knowledge graph, proprietary methods, scientific literature and other sources to generate, triage and rationalise testable therapeutic hypotheses for rare diseases
You won’t be starting from scratch
We’ve adopted an agentic framework (our stack currently includes Python, ADK and AgentSpace) and built workflows already delivering impact across our drug discovery platform
But this is a fast-moving field, so a big part of the role is helping us adapt as the landscape shifts
You’ll work alongside the technical lead who owns our agentic infrastructure, with scope to take ownership of specific workflows and grow your influence as you do
You’ll join a cross-functional team of machine learning engineers, software engineers, bioinformaticians, drug discovery scientists and clinicians, all working to sharpen how Healx makes better decisions in drug discovery
Build and refine AI-agentic workflows on our internal framework to help drug discovery scientists generate the best testable therapeutic hypotheses to progress
Translate discovery problems into agent designs, working out where an agentic approach genuinely adds value, and where it doesn’t
Integrate agents with our knowledge graph, proprietary methods, scientific literature and other sources so they reason over the right evidence for each problem
Expand and maintain our existing GenAI tools so they keep pace with the team’s needs and a fast-moving ecosystem
Contribute to how we evaluate agentic workflows, helping shape sensible evals, testing and quality standards as the practice matures
Write clear, maintainable, well-documented code that others on the team can build on
What success looks like:
In 3 months, you have:
Got to grips with our agentic framework and the discovery problems it serves, and made your first contributions land in the codebase
Built working relationships with the scientists and engineers you partner with, and started turning their feedback into concrete improvements
In 6 months you have:
Taken at least one agentic workflow from idea to a production tool scientists use in our drug discovery pipeline — built on our framework, with sensible evaluation and documentation
Operating with real independence — owning agentic workflows end to end, proposing improvements
Benefits
Share options
Remote and flexible working
Enhanced parental leave
Quarterly socials
Private medical insurance
Life insurance
Generous pension contributions
Preferred experience
You have at least 2 years of software engineer or ML engineer working experience. And you have strong software engineering fundamentals — you write clear, tested, maintainable Python code that others can build on
You’ve built and shipped LLM-agentic systems that deliver real value — agents that use tools, orchestrate multi-step workflows and behave reliably in production
Fluency with the modern LLM/agent toolkit — model APIs, prompting, tool use, RAG, and the patterns this fast-moving ecosystem is converging on (MCP, agent frameworks, evals)
You enjoy working closely with non-engineers — you are the kind of person who’ll sit with a scientist to understand what they actually need
Experience in drug discovery, biology, or another life science domain
Experience building evaluation harnesses or testing strategies for LLM systems
Familiarity with knowledge graphs or reasoning over structured or heterogeneous data
A track record of picking up unfamiliar domains quickly and becoming useful fast
Interest in or experience with biotech / techbio and its impact on patient outcomes
