ML Engineer

Vortexa; City Of London; On-site; GBP 70,000 - 90,000; Full time

Job summary

A leading energy data company in London seeks a Machine Learning Engineer responsible for designing and building scalable ML pipelines. The ideal candidate will collaborate with energy analysts and engineers, leveraging strong skills in Python, Kubernetes, and MLflow. This role offers flexible hybrid working, a vibrant culture, and opportunities for continuous learning and equity options.

Benefits

Flexible hybrid working

Private Health Insurance

Equity options

Qualifications

• Experience in building and deploying distributed scalable ML pipelines.
• Solid machine learning engineering fundamentals; experienced with classification models and anomaly detection.
• Knowledgeable about data privacy regulations in the energy sector.

Responsibilities

• Design and build distributed, scalable ML pipelines processing energy data.
• Develop classification models and anomaly detection systems.
• Collaborate with energy analysts and engineers for production-ready ML systems.

Skills

Fluency in Python

Kubernetes

MLflow

XGBoost

Anomaly detection

Classification models

Data lineage tracking

AWS services

Apache Kafka

Tools

ML pipelines

Terraform

CloudFormation

Job description

Overview

Processing thousands of energy data points per second from diverse operational sources, handling massive volumes of energy data while running sophisticated classification and anomaly detection models in real-time, maintaining comprehensive data lineage, and delivering insights through high-performance platforms used by energy operators globally requires exceptional engineering and scientific expertise. This processing demands models that can withstand the scrutiny of energy analysts and traders, operations teams, and regulatory bodies, with the performance, stability, and reliability that critical energy systems require.

The Data Platform Team is responsible for all machine learning operations across our energy data ecosystem. We work with raw sensor data from millions of energy assets to complex operational datasets, generating high-value predictions such as equipment failure detection, energy demand forecasting, operational anomaly identification, predictive maintenance scheduling, and system optimization recommendations.

The team has built a comprehensive suite of statistical and machine learning models that enable us to provide the most accurate and actionable insights into energy operations. We apply cutting-edge research to real-world energy challenges in a robust, scalable, and maintainable way, with model quality continuously validated by experienced in-house energy analysts, traders, and domain experts to ensure reliability of our predictions.

You'll be instrumental in designing and building ML infrastructure and applications to propel the design, deployment, and monitoring of existing and new ML pipelines and models. Working with software engineers, data scientists, and energy analysts and traders, you'll bridge the gap between research experiments and production energy systems by ensuring 100% uptime and bulletproof fault-tolerance of every component of our ML platform.

Responsibilities

• Design and build distributed, scalable ML pipelines that can process large volumes of energy data daily using Kubernetes and MLflow.
• Apply solid ML engineering fundamentals, with fluency in Python, PyTorch, and XGBoost; develop classification models and anomaly detection systems for production environments; implement comprehensive data lineage tracking and model governance.
• Collaborate with energy analysts, traders, and engineers to ensure reliable, production-ready ML systems with strong uptime and fault-tolerance.

Qualifications

• Experience in building and deploying distributed scalable ML pipelines that process large volumes of energy data daily using Kubernetes and MLflow.
• Solid machine learning engineering fundamentals; fluent in Python, PyTorch, and XGBoost; experience with classification models and anomaly detection in production; capable of implementing data lineage tracking and model governance.
• Experience with the full ML model lifecycle: experiment design, model development, validation, deployment, monitoring, and maintenance.
• Driven by working in an intellectually engaging environment with energy analysts and traders, where constructive challenges and technical debates are encouraged.
• Comfortable in a dynamic environment, eager to bring ML innovations to production, and with a positive can-do attitude.
• Interested in mentoring team members and helping them grow their ML engineering skills.
• Experience with AWS services (SageMaker, S3, EC2, Lambda, etc.) and infrastructure as code tools (Terraform, CloudFormation).
• Familiarity with Apache Kafka and real-time streaming frameworks, observability practices (logging, monitoring, distributed tracing) for ML systems, transformer architectures, and time-series analysis relevant to energy applications.
• Knowledgeable about data privacy regulations and compliance frameworks in the energy sector.

Nice to Have

• Experience in the energy sector or understanding of energy systems and operations.
• Experience with time series forecasting techniques relevant to energy applications.
• Familiarity with generative AI applications in operational contexts.

Benefits and Culture

• Flexible hybrid working – split your time between home and our office, with the freedom to work where you’re most productive.
• A vibrant, diverse company pushing technology to deliver beyond the cutting edge.
• A team of motivated professionals striving to be the best at what we do.
• Opportunities for constant learning and exploration of new tools and technologies.
• Equity options for all staff, enabling company ownership in a business-savvy and responsible way.
• Collaborative culture with a focus on teamwork and shared success.
• Private Health Insurance with Vitality to support your health.
• Global Volunteering Policy to help you contribute to the community.