Machine Learning System Engineer

ML System Engineer 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, s e c ure a n d sustainable. We are growing fast, having closed a recent funding round and looking to accelerate rapidly. O c t aiPipe i s 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 a Machine Learning Systems Engineer to join our Physical Modelling team. You'll build and scale the platform that takes our machine learning models from research into reliable production, covering deployment, model serving, monitoring and automated retraining across customer sites. Working closely with our Applied Scientists, who define what the models should do and when, you'll own how they're deployed, operated and continuously improved in the real world. As the number of live deployments grows, you'll play a key role in ensuring our ML systems remain scalable, resilient and reliable. Duties and responsibilities Design, build and operate the systems that take machine-learning models from research to production — training, evaluation, deployment and serving. Build and maintain containerised services and APIs for model training, inference and evaluation. Own model lifecycle management: versioning, release, rollout and rollback across a growing number of production deployments. Build monitoring and observability for models and data in production . Automate retraining, evaluation and deployment workflows to run reliably with minimal manual intervention . Work closely with applied scientists to productionise research: turn prototypes and specifications into robust, maintainable systems. Continuously reduce manual effort across the model lifecycle through automation and standardisation. Your profile Strong software engineering skills in Python — production code, tests and documentation . Experience building and operating machine-learning systems in production: model serving, training or inference pipelines, and GPU workloads. Docker and containerisation, CI/CD, API design ( FastAPI or similar), and solid Linux fundamentals. Experience deploying software beyond managed cloud — on-premise , edge or customer-premise environments with real resource and connectivity constraints. Observability practice: metrics, logging and alerting for production systems. You also might have Experience with MLOps tooling and practices: model registries and experiment tracking ( MLflow , Weights & Biases or similar), or pipeline orchestration (Airflow, Prefect, Kubeflow or similar). Kubernetes experience, or experience operating industrial, IoT or edge fleets. Experience orchestrating distributed or scheduled training jobs. Data-engineering experience with time-series or telemetry data. Experience hardening software that runs on customer premises. Exposure to energy systems, HVAC or building controls. 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.