Octaipipe logo

Applied Scientist – Predictive Health & Maintenance (PHM)

Hiring from
United Kingdom
Work type
Hybrid
Posted

624,317 remote jobs, straight from company career pages

100% free · New jobs every minute

Show job description

Applied Scientist – Predictive Health & Maintenance (PHM)

Machine Learning · Physical Modelling Team


The Company

OctaiPipe is a young, ambitious company with the vision to be the global driving force for the next paradigm of foundational, physical AI that ensures our connected world, and its critical infrastructure, is safe, secure and sustainable. We are growing fast, having closed a recent funding round and looking to accelerate rapidly. OctaiPipe is offering the right candidate an exciting role on this adventure!


OctaiPipe is on a mission to revolutionise the optimisation of energy in data centres through decentralised artificial intelligence (AI). To do this, OctaiPipe is harnessing an elegant but revolutionary idea. Rather than move the data from the source, move the algorithms to the data to learn at the data source. This learning can be achieved with the intelligence of many devices through novel federated AI technology. OctaiPipe is developing the AI for Cooling Efficiency (ACE) application to be deployed using its own in-house distributed AI platform.


The Role

We are looking for an Applied Scientist specialising in Predictive Health & Maintenance (PHM) to join our Physical Modelling team.

You'll develop machine-learning models and methodologies to monitor the health, performance and reliability of critical industrial assets, with an initial focus on data centre cooling infrastructure.


Working with real-world operational data, you'll explore how to detect anomalies, identify early signs of degradation and predict potential equipment failures before they occur. You'll combine data-driven approaches with an understanding of physical systems to develop models that support more proactive and reliable asset management.


You'll frame research questions, design and run experiments, and translate findings into robust solutions that our engineering teams can take into production. A key part of the role is understanding how these models perform in complex operational environments, particularly where failures are rare, data is imperfect and reliability is critical.


Duties and responsibilities

  • Research, develop and evaluate machine-learning approaches for predictive health monitoring, anomaly detection, fault diagnosis and equipment failure prediction.
  • Develop models that identify changes in asset behaviour, detect early signs of degradation and support predictive maintenance decisions.
  • Explore approaches to estimating asset health, degradation trajectories and remaining useful life (RUL).
  • Work with multivariate time-series and sensor data from real industrial systems, addressing challenges such as noisy, incomplete or limited data.
  • Investigate how physical modelling, surrogate models and digital twins can improve fault detection, diagnostics and predictions of asset health.
  • Design and run experiments to assess model accuracy, robustness, uncertainty and generalisation across different assets and operating conditions.
  • Help develop methods for adapting and improving deployed models as new operational data becomes available.
  • Collaborate closely with applied scientists, engineers and neighbouring teams to translate research into practical, production-ready solutions.
  • Communicate research findings, technical trade-offs and model limitations clearly to technical and non-technical audiences.


Your profile

  • A strong background in machine learning, applied mathematics, engineering or a related quantitative discipline, demonstrated through a PhD, relevant industry experience or equivalent applied research.
  • Hands-on experience developing and evaluating machine-learning models for time-series analysis, anomaly detection, fault diagnosis or predictive modelling.
  • Strong Python programming skills and experience with machine-learning frameworks such as PyTorch or similar.
  • Experience working with complex, noisy or imperfect real-world datasets, ideally involving sensor or operational data.
  • An understanding of statistical modelling, uncertainty estimation and rigorous model evaluation.
  • The ability to independently frame technical problems, design experiments and develop solutions from initial research through to practical application.
  • A rigorous empirical mindset, with an appreciation of model limitations, failure modes and the challenges of deploying machine learning in real-world environments.
  • Clear written and verbal communication skills and the ability to collaborate effectively across disciplines.
  • Experience developing predictive maintenance, condition monitoring or prognostics solutions for industrial equipment.
  • Knowledge of reliability engineering, fault detection and diagnosis, or remaining useful life estimation.


You also might have

  • Experience applying machine learning to physical systems such as HVAC, cooling equipment, energy systems, manufacturing or other industrial processes.
  • Familiarity with physics-informed machine learning, digital twins or hybrid physics/data-driven modelling.
  • Experience with limited failure data, class imbalance, simulation-based training or transfer learning across different assets.
  • Knowledge of continual learning, Bayesian methods or uncertainty quantification.
  • Experience deploying machine-learning models into production alongside engineering teams.
  • Publications or open-source contributions in relevant areas.


Why Join OctaiPipe

  • Work on real-world sustainability impact at global scale
  • Influence how AI is responsibly applied to critical infrastructure
  • Join a well-funded, rapidly growing scale-up with ambitious goals
  • Collaborate with experts across AI, infrastructure, and operations
  • Shape a product that can materially reduce energy use and carbon emissions worldwide


The above statements are not intended to encompass all functions and qualifications of the position; rather, they are intended to provide a general framework of the requirements of the position. Job incumbents may be required to perform other functions not specifically addressed in this description.

Similar jobs

Apply for this job100% free