Senior MLOps Engineer – Edge AI & Production Infra

MFK Recruitment; Brentford; Hybrid; GBP 70,000 - 100,000; Full time

Job summary

MFK Recruitment is recruiting a Senior MLOps Engineer for a UK technology company developing AI/ML solutions for defence, security and demanding environments. The role focuses on moving models from research to reliable production with scalable training, deployment and monitoring.

You will work across cloud and edge platforms, including NVIDIA Jetson systems, building robust CI/CD, model registries and inference optimisations while collaborating with AI and software engineers and customers.

Qualifications

• Experience with ML experiment tracking and model registries.
• Hands-on experience with distributed training frameworks.
• Experience enhancing production inference performance.

Responsibilities

• Implement and manage ML experiment-tracking and model-registry infrastructure.
• Optimise models for production using inference acceleration, quantisation and pruning.
• Build containerised deployment pipelines for cloud, x86 and edge-device architectures.
• Develop and maintain CI/CD pipelines for automated testing, building and deployment.
• Manage GPU-accelerated edge deployment and video-analytics infrastructure.
• Work closely with AI Engineers, Software Engineers and customers to productionise models.
• Contribute to technical planning, architecture decisions and engineering best practices.

Skills

MLops

Distributed training

Model deployment

Experiment tracking

CI/CD

Edge devices

Cloud platforms

Monitoring

Docker

Kubernetes

NVIDIA Jetson

GPGPU

Python

Tools

MLflow

Weights & Biases

Neptune

ClearML

Ray

DeepSpeed

TorchServe

TensorRT

ONNX Runtime

OpenVINO

GStreamer

FFmpeg

Prometheus

Grafana

Datadog

Kubeflow

ECS

Nomad

Airflow

Dagster

Metaflow

Kafka

Pulsar

Redis Streams

RabbitMQ

TorchServe

DVC

Job description

MFK Recruitment is recruiting a Senior MLOps Engineer for a UK technology company developing AI/ML solutions for defence, security and demanding environments. The role focuses on moving models from research to reliable production with scalable training, deployment and monitoring.

You will work across cloud and edge platforms, including NVIDIA Jetson systems, building robust CI/CD, model registries and inference optimisations while collaborating with AI and software engineers and customers.