Senior AI/ML Engineer - Materials Discovery

Contract: Full-time, permanent
Location: Hybrid (London office)
Level: 3-5 years professional experience

About Materiom

Materiom's mission is to create a world where materials regenerate nature and support human health. We pursue it by building data and AI tools that help discover natural alternatives for packaging, textiles, and the built environment. We support innovators around the world to bring these new materials to market.

We're an interdisciplinary team bringing together materials engineering, computational materials science, AI/ML engineering, and business innovation. In 2026, we're at an inflection point: with advanced AI and a self-driving lab, we are accelerating the discovery of natural materials and supporting innovators across the sector.

The role

This is a high-impact role with the potential to apply leading AI/ML to one of the world's greatest challenges. We're looking for a Senior AI Engineer to work at the intersection of applied ML, applied AI, and our self-driving lab; someone excited about the potential of AI for scientific discovery, with deep expertise in ML model development for predictive modelling and representation learning, keen to work on applying AI for science.

You'll work within our technical team to contribute across three primary workstreams:

• Predictive modelling & representation learning: developing and iterating on ML models that learn the high-dimensional, multi-objective, natural polymers design space.
• Efficient data sampling techniques: developing and consolidating Bayesian optimization and active learning scientific workflows for experimental & in-silico data generation campaigns.
• Material discovery agentic systems: collaborate with our technical team in developing and evaluating internal & external tooling that integrate Materiom’s data and model intelligence into AI agents for scientific discovery.

What you'll do

ML modeling 

• Design, build, and deploy structure property prediction ML models of bio-based formulations from experimental, in-silico and literature-mined data. In pursuit of a base model that generalizes across materials systems.
• Develop rigorous evaluation pipelines and experiments to compare modelling approaches, interpret results clearly, and iterate against internal performance benchmarks.