Machine Learning Engineering, Computational Simulation

EntroMetrix; Greater London; On-site; GBP 65,000 - 95,000; Full time

Benefits offered by this job

Unlimited coffee

Competitive compensation package

London office

Job summary

EntroMetrix is building physics-informed AI to help industrial teams run more efficient and resilient operations from its London office. We seek a hands-on Machine Learning Engineer to design, train and deploy models that handle messy real-world data and respect physical constraints.

You will work with our founding team, customer sites and industrial data to turn early validation into a scalable product, training end-to-end systems and contributing to platform direction.

Qualifications

• Degree in machine learning, computer science, engineering, physics or related STEM field from a world-leading university (PhD-level).
• Strong practical experience building ML models in Python, preferably with PyTorch or JAX.
• Experience with scientific ML, time-series modelling, optimisation, simulation or probabilistic modelling.

Responsibilities

• Design, train and deploy ML models for complex operational systems.
• Work with sparse, noisy and irregular time-series data from real-world environments.
• Build models that combine data-driven learning with physical/operational constraints.
• Develop reusable modelling components scalable across sites and use cases.
• Collaborate with product/engineering to move models from prototype to production.
• Evaluate model performance, reliability and robustness in applied settings.
• Engage with customers to understand operational context behind the data.
• Help define the technical direction of the platform as an early ML hire.

Skills

Python

PyTorch

JAX

Time-series modelling

Physics-informed ML

Education

PhD in ML/CS/Engineering/Physics

Tools

PyTorch

JAX

Job description

About Us

Manufacturing is one of the biggest, hardest and most important systems in the world, but many factories still make critical operational decisions with fragmented data and limited intelligence. EntroMetrix is changing that by building physics-informed AI that helps industrial teams run more efficient, resilient and sustainable operations.

We are a small team founded by engineers from Cambridge and Imperial, working on a problem where better software can have a real-world impact on energy, materials and production. If you want to build serious technology, work close to real industrial customers and have a direct hand in shaping an early company, EntroMetrix is the place to do it. We are hiring across a number of roles. If you're a fit, apply.

Role

We are looking for a Machine Learning Engineer to help build frontier models that understand and improve complex operational systems.

The work sits at the intersection of scientific machine learning, time-series modelling, optimisation and real-world deployment. You will work closely with the founding team, customer sites and industrial data to turn early technical validation into a scalable product.

This is a hands-on engineering role. You will not just train models in isolation. You will build systems that work with messy data, operational constraints and real-world environments.

What you will do

• Design, train and deploy machine learning models for complex operational systems.
• Work with sparse, noisy and irregular time-series data from real-world environments.
• Build models that combine data-driven learning with physical and operational constraints.
• Develop reusable modelling components that can scale across different sites and use cases.
• Work with the product and engineering team to move models from prototype to production.
• Evaluate model performance, reliability and robustness in applied settings.
• Spend time with customers to understand the operational context behind the data.
• Contribute to the technical direction of the platform as one of the first ML hires.

What we are looking for

• A degree in machine learning, computer science, engineering, physics, mathematics, applied mathematics, operations research or a closely related STEM field from a world-leading university (PhD-level).
• Strong practical experience building machine learning models in Python, ideally using PyTorch, JAX or similar frameworks.
• Experience with one or more of scientific machine learning, physics-informed ML, time-series modelling, optimisation, simulation, forecasting or probabilistic modelling.
• Comfort working with messy real-world data, including missing values, drift, noise and inconsistent data quality.
• Interest in applying machine learning to physical systems, industrial operations and real-world optimisation problems.
• Willingness to work in person from our London office, typically 4 to 5 days per week, with occasional travel to customer sites in the UK.

Nice to have

• Experience deploying ML models into production.
• Experience with optimisation, simulation, control systems or operations research.
• Exposure to industrial or operational data environments.
• Experience with Bayesian approaches, multi-fidelity data streams, symbolic regression, glass-box modelling or reinforcement learning.
• Publications or research experience in scientific ML, machine learning for physical systems or applied optimisation.
• Competitive compensation package.
• Ownership of a critical technical layer at an early-stage company.
• The chance to build frontier AI models that help define how factories are run over the next decade.
• Work directly with manufacturers across sectors, from large enterprises to SMEs, and see your models deployed in real operations to help decarbonise industry and improve operational resilience.
• A small, technical founding team with high ownership, honest feedback and no theatre.
• Unlimited coffee

These are in-person roles based in London. We are currently unable to offer visa sponsorship, applicants must already have the right to work in the UK.