Senior Machine Learning Engineer (IIoT & OT Security)

About the Company

We are recruiting on behalf of an innovative technology company developing advanced cybersecurity and network-monitoring technology for Industrial IoT (IIoT) and Operational Technology (OT) environments.

The company is building intelligent, autonomous monitoring infrastructure designed to protect critical industrial systems—including manufacturing environments, utilities and energy infrastructure—from cyber threats, operational failures and abnormal network behaviour.

At the heart of the platform is the use of machine learning to distinguish genuine cyberattacks from benign operational anomalies

The Role

We are looking for an experienced Senior Machine Learning Engineer to take a leading role in the development of the company's Operational Technology Network Intrusion Detection System (NIDS).

This is a key technical role focused on transforming large volumes of semi-structured network telemetry, primarily JSON, into real-time and actionable security intelligence.

You will design and deploy machine learning pipelines capable of distinguishing cyber threats from physical equipment and operational anomalies, helping to improve resilience, security and uptime across industrial environments.

Why Consider the Role?

• High-Impact Work: Contribute directly to protecting critical industrial infrastructure from cyber and operational risks.
• Technical Challenge: Tackle complex anomaly detection and zero-day threat detection across large-scale operational data.
• Greenfield Environment: Play a central role in developing and scaling a technology platform from the ground up.
• Technical Ownership: Take significant ownership of the ML architecture, pipelines and production systems.

Key Responsibilities

1. Advanced ML Pipeline \& Data Engineering

• High-Performance Telemetry Ingestion: Design optimised parsers and data pipelines to ingest, flatten and feature-engineer complex, nested JSON network packets and industrial protocol payloads at scale.
• Model Development: Build, train and validate unsupervised anomaly detection, time-series forecasting and deep learning architectures designed for zero-day threat detection.
• Differentiated Classification: Develop algorithms capable of distinguishing security incidents such as lateral movement and unauthorised commands from operational anomalies such as PLC misconfiguration, equipment drift and packet loss.

2. AI Innovation \& Feature Engineering

• Explainable AI (XAI): Integrate frameworks such as SHAP or LIME into the alerting engine to provide transparent, human-readable insights and root-cause analysis.
• Automated Asset Discovery: Use clustering and behavioural analysis to fingerprint, profile and automatically inventory network assets based on traffic metadata.
• Predictive Maintenance: Analyse historical telemetry to predict network switch failures and bandwidth congestion before they impact operations.
• Smart Policy Synthesis: Use traffic-flow analytics to recommend zero-trust firewall configurations and micro-segmentation policies.

3. Production Deployment \& MLOps

• Edge Deployment: Containerise and deploy resource-efficient models using technologies such as Docker and Kubernetes, suitable for industrial edge and centralised cloud environments.
• Robust MLOps: Establish and maintain MLOps practices using platforms such as MLflow, Weights \& Biases or Kubeflow, with a focus on model drift, concept drift and performance degradation.

What We're Looking ForEssential Experience

• 5+ years of professional experience developing and productionising machine learning systems.
• Strong commercial experience with Python.
• Strong knowledge of NumPy, Pandas and Scikit-Learn.
• Hands-on experience with PyTorch and/or TensorFlow.
• Experience developing production ML models using unsupervised or semi-supervised learning.
• Strong experience processing and analysing large or complex datasets, including semi-structured or nested data.
• Experience with distributed or streaming technologies such as Kafka, Spark or Flink.
• Experience deploying machine learning models into production environments.
• Good understanding of software engineering principles, testing and maintainable production code.

Networking \& Security Knowledge

You should have a strong understanding of networking fundamentals, including:

• TCP/IP;
• the OSI model;
• network flows and packet behaviour;
• PCAP or packet-level network analysis.

Previous cybersecurity experience is highly desirable, particularly where machine learning has been applied to network monitoring, threat detection or behavioural analytics.

Highly Desirable Experience

Experience in one or more of the following would be particularly valuable:

• Network Intrusion Detection Systems (NIDS);
• cybersecurity or SIEM product development;
• Industrial IoT or Operational Technology;
• industrial protocols such as Modbus, DNP3, BACnet, OPC UA or Profinet;
• graph neural networks or graph-based behavioural modelling;
• time-series anomaly detection;
• explainable AI techniques such as SHAP;
• model optimisation for edge deployment;
• ONNX or TensorRT;
• Kubernetes-based ML infrastructure;
• predictive maintenance or industrial analytics.

Direct OT security experience is advantageous but is not essential if you have strong machine learning, networking and production engineering experience.

Qualifications

A Bachelor's, Master's or PhD in Computer Science, Machine Learning, Data Science, Cybersecurity, Mathematics, Engineering or another relevant quantitative discipline is desirable.

Equivalent commercial experience will also be considered.

The Offer

• Competitive Compensation: Competitive salary package with performance-linked equity.
• Impact: The opportunity to contribute to AI-driven cybersecurity and the protection of critical infrastructure.
• Technical Ownership: The opportunity to play a significant role in shaping the ML architecture and technology of a growing platform.

Pay: From £50,000.00 per year

Ability to commute/relocate

• London EC3V 9BS: reliably commute or plan to relocate before starting work (required)

Education

• Bachelor's (preferred)

Experience

• professional Machine Learning Engineering: 5 years (preferred)

Work authorisation

• United Kingdom (required)

Work Location: In person