Machine Learning Scientist (KTP Associate) in AI-Driven Peptide Design
Collaborative KTP role to develop AI platforms for peptide sequence generation and property prediction in drug discovery.
Best for:Best for PhD-level machine learning scientists with expertise in bioinformatics, computational biology, or AI-driven drug discovery, seeking industry-academia collaboration in peptide design.
Overview
This Knowledge Transfer Partnership (KTP) position bridges Queen Mary University of London and AstraZeneca to advance AI-driven peptide design. The successful candidate will work at AstraZeneca’s Cambridge facility while being employed by QMUL, contributing to an AI platform for generating novel peptide sequences and predicting key biological properties. The role involves interdisciplinary research at the intersection of machine learning, bioinformatics, and computational biology, with a focus on therapeutic applications. The project aims to leverage large-scale datasets to learn structure-property relationships, ultimately accelerating drug discovery. Ideal candidates should have a strong computational background and interest in biological sequence modeling.
What you'll do
- Develop and implement AI models for generating novel peptide sequences with desired biological and biophysical properties.
- Predict key peptide characteristics such as affinity, stability, permeability, and developability using machine learning techniques.
- Analyze large-scale experimental and computational datasets to learn structure-property relationships in peptides.
- Collaborate with AstraZeneca researchers to integrate AI tools into their drug discovery pipeline.
- Travel periodically to Queen Mary University of London for research and training purposes.
- Contribute to the development of an advanced AI platform for peptide design, bridging academia and industry.
- Engage in knowledge transfer activities to facilitate innovation between Queen Mary and AstraZeneca.
Requirements
Degree required: PhD in computer science, bioinformatics, computational biology/chemistry, artificial intelligence, or a related discipline (or near completion).
Language: English; proficiency required for collaboration and reporting.
Instruction: English
- Proven expertise in machine learning, particularly in biological sequence modeling.
- Experience with AI-driven drug discovery or peptide design.
- Strong computational skills, including programming in Python or similar languages.
- Familiarity with large-scale data analysis and machine learning algorithms.
- Interest in biological sequence modeling and therapeutic design.
- Open to candidates with or near completion of a PhD in relevant fields.
- No specific nationality or residency restrictions mentioned.
Funding & terms
How to apply
Deadline: 2026-10-20
Applicants must submit their CV and cover letter through the external application portal provided. The application process involves reviewing qualifications, research experience, and alignment with the project goals. Shortlisted candidates will be invited for interviews.
- CV
- Cover letter
- Proof of PhD completion or near-completion (if applicable)
Create a free profile to unlock your personal match score, the full requirements, funding details and how to apply — in English or Persian.