Machine Learning Performance Engineer, London

Machine Learning Performance Engineer, London

We are here to advance human health, by reimagining drug discovery with the power and pace of artificial intelligence.

The future is coming. A future enabled and enriched by the incredible power of machine learning. A future in which diseases are curtailed or cured by better and faster drug discovery.

Our values exist in service of that future. We think they’ll help us bring it closer, too.

Come and be part of an interdisciplinary team driving groundbreaking innovation and play a meaningful role in contributing towards us achieving our ambitious goals, while being a part of an inspiring and collaborative culture.

The world we want tomorrow is the one we’re building today. It starts with the culture at this company. It starts with you.

Your impact

We are looking for engineers with different levels of experience – Mid through to Senior, Staff or equivalent levels.

This is an exciting opportunity for you to shape the new performance and scaling focused capability of Isomorphic Labs.

What you will do

• Develop custom GPU kernels maximising utilisation and application performance.
• Help design, implement, and optimize advanced distributed training and inference strategies.
• Implement low-level optimisations to overcome hardware limitations.
• Design low-precision algorithms balancing high performance with minimal accuracy loss.
• Use your intuitions of both runtime and hardware to optimize performance for both latency and throughput on real world drug design programs.
• Partner with technical infrastructure teams to deploy solutions and manage training uptime.
• Work with ML engineers and researchers to create efficient training and inference model architectures.

Skills and qualifications

Essential:

• Strong working knowledge of HPC and ML Systems.
• Good understanding of GPU and other AI accelerator architectures.
• Strong knowledge of data structures and algorithms.
• Good working knowledge of maths / linear algebra.
• Experience with deep learning ML frameworks (preferably JAX).
• Excellent collaboration skills.

Nice to have:

• Knowledge of XLA, Triton, CUDA, Pallas or similar accelerator DSLs / compiler stacks.
• Experience with distributed training and data/model sharding strategies.
• Knowledge of collective communication libraries (e.g. NCCL).
• Proven ability to optimise ML accuracy with low-precision formats.
• Experience building, deploying and maintaining production systems on GCP.
• Interest in chemistry and biology.

Culture and values
We are guided by our shared values. It’s not about finding people who think and act in the same way. These values help to guide our work and will continue to strengthen it.

Thoughtful
Thoughtful at Iso is about curiosity, creativity and care. It is about good people doing good, rigorous and future-making science every single day.

Brave
Brave at Iso is about fearlessness, but it’s also about initiative and integrity. The scale of the challenge demands nothing less.

Determined
Determined at Iso is the way we pursue our goal. It’s a confidence in our hypothesis, as well as the urgency and agility needed to deliver on it. Because disease won’t wait, so neither should we.

Hybrid working

It’s hugely important for us to share knowledge and build strong relationships with each other, and we find it easier to do this if we spend time together in person. This is why we follow a hybrid model, and would require you to be able to come into the office 3 days a week (currently Tuesday, Wednesday, and one other day depending on which team you’re in). If you have additional needs that would prevent you from following this hybrid approach, we’d be happy to talk through these if you’re selected for an initial screening call.