Senior Machine Learning Platform Engineer

Mustard Systems is a team of roughly 65 people dedicated to developing market leading sports models and trading strategies. Applications of our research are widespread across multiple sectors including betting, insurance, finance and the media, as well as giving advice to coaches and owners of sporting teams. Our aim is to predict sport as accurately as possible, and we achieve this by combining large, rapidly changing datasets with home grown software and statistical models.

We enjoy a fast-paced, ever-changing environment, offering fresh challenges which are both rewarding and enjoyable. Our ambitions are high, aiming to create best-in-class systems in a highly competitive field. In the coming year, we will be working on expanding our trading strategies and data feeds.

Why this role exists

This is a new role. Our quants have built an evolving array of processes and models, and we want to reduce the time they spend engineering processes so they can focus on the next generation of our models. We want an experienced engineer who will look at how we work, tell us what to change, architect, and then deliver changes to our platform and approaches.

What you will own

• Architecture. Find the weak points in the systems our quants depend on, then propose and deliver better ones. This includes how we use compute, both on our own hardware and in the cloud.
• Tooling. Build shared tools so that quants stop doing the same repetitive engineering work again and again.
• Technical direction. Bring in new technology when it gives a real improvement, and own its introduction. Write down the important decisions so that no system depends on one person.
• Performance. Profile and speed up the workloads that matter most: simulation, model training, validation and backtesting. This covers CPU, memory, I/O and parallelism.
• The path to production. Make it reliable to move work from a research notebook to something that runs every day, with tests, monitoring and reproducible environments.

You own your work from end to end. You find the problem, deliver the fix, run it, and measure the result.

You will work closely with Quant, Development, Infrastructure and Data teams.

Our technical stack

• Python/Cython (pandas, NumPy, SciPy, PyArrow)
• Jupyter
• Parquet (and some legacy HDF5)
• Snowflake
• PostgreSQL
• GitLab
• bash

• Strong Python, with a record of making numerical or data-heavy code measurably performant and reliable (profiling, vectorisation, Cython/Numba or similar, parallelism).
• Experience designing and owning systems that other people use, ideally researchers, data scientists or analysts.
• Good judgement on architecture and trade-offs: when to build, when to reuse, and when to leave something alone.
• Production engineering habits: testing, observability, reproducible environments, CI.
• The confidence to set your own direction when the problem is not clearly defined, and the communication skills to bring other people with you.

• Work on cutting-edge systems in a competitive and innovative field.
• Collaborate with a smart, driven team, where your contributions directly impact business performance.
• Opportunity to drive the company’s technical direction and double its revenue in the next three years.

Comprehensive benefits, including:

• Competitive salary and significant bonus potential (up to 30%).
• Enhanced pension match with salary sacrifice option.
• Health insurance and life assurance.
• Sabbatical leave after five years.
• 33 days of annual leave (including bank holidays).

We have a hybrid working approach at Mustard Systems. We enjoy working and collaborating together and require people to be in our Hammersmith office three days a week. If you require any additional flexibility, please let our hiring team know as part of the recruitment process.