Back to search
AI Engineer - Bioinformatics Chat Platform, TechBio Scaleup
Circa £90k + Share Options, Private Health
Oxfordshire - hybrid working
A one-off opportunity for a mid to senior level AI engineer to join a seriously innovative TechBio scaleup (~30 people) developing novel cancer biologics.
We're seeking an AI Engineer to lead development of a conversational AI platform for structural biology and bioinformatics. This platform will democratize access to complex protein structure analysis through natural language interactions, integrating with existing databases and computational pipelines.
The AI Engineer will have core expertise in AI, LLMs, NLP frameworks - together with a software focus (Python, APIs, SQL, cloud) including proven experience of delivering products to clients.
The role:- Design and implement LLM-powered conversational interfaces for bioinformatics workflows
- Build function-calling systems that integrate Claude/OpenAI models with structural biology tools
- Develop context-aware chat systems that maintain conversation history across sessions
- Create modular, scalable architectures for bioinformatics data processing
- Integrate with protein structure databases (PDB, AlphaFold, custom TCR structures)
- Build APIs connecting LLMs to molecular visualization tools (PyMOL, ChimeraX, NGLView)
- Develop specialized functions for TCR-peptide-HLA interface analysis
- Create automated workflows for immune repertoire data processing
- Design PostgreSQL schemas for storing structural and sequence data
- Implement efficient data retrieval systems for large-scale protein datasets
- Build real-time data pipelines for immune repertoire analysis
- Optimize database performance for molecular structure queries
- Create intuitive chat interfaces using Streamlit or similar frameworks
- Develop specialized prompting strategies for bioinformatics use cases
- Build collaborative features for team-based structural analysis
- Design educational components that explain complex biology concepts
- 3+ years hands-on experience (predominantly industry gained) with LLMs (GPT, BERT, T5, Claude) and NLP frameworks
- Proficiency in prompt engineering, fine-tuning, and function-calling architectures
- Experience with Hugging Face, OpenAI APIs, and transformer libraries
- Understanding of model customization for domain-specific tasks
- Experience with retrieval-augmented generation (RAG) systems
- Knowledge of optimization techniques for reducing LLM latency and computational costs
- Strong Python development skills (pandas, numpy, scikit-learn, PyTorch/TensorFlow)
- Experience with web frameworks (Streamlit, FastAPI, or Flask) and frontend technologies
- Database design and optimization (PostgreSQL preferred) for large protein datasets
- API development and integration, especially for interfacing LLMs with external systems
- Microservices architecture and containerization (Docker, Kubernetes)
- Version control, CI/CD pipelines, and automated testing practices
- Understanding of software design patterns for scalable, maintainable LLM applications
- Experience with cloud computing platforms (AWS, GCP, Azure) and big data technologies
- Familiarity with DevOps practices and deployment of ML applications
- Data preprocessing and pipeline automation for structured/unstructured biological data
- Understanding of data security and compliance requirements for sensitive datasets
Bioinformatics & domain knowledge is strongly advantageous, though is NOT a pre-requisite.
Benefits:In addition to a competitive salary, share options, private health, you will enjoy access to state-of-the-art computational resources and cutting-edge biological datasets; latest bioinformatics software, LLM frameworks, and protein modelling tools; the opportunity to work with novel therapeutic targets and protein engineering challenges.
This is an urgent requirement. Immediate availability or availability to start inside 4 weeks preferred.
