Senior ML Engineer: Real-Time Vision at Scale (London)

Dex

Greater London

On-site

GBP 120,000 - 180,000

Full time

11 days ago

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Dex is seeking a highly experienced ML systems engineer to architect and operate real-time multimodal model serving at scale in London. You will own GPU utilisation, latency, and throughput optimisations across PyTorch, CUDA, Kubernetes on AWS/GCP, delivering robust production-ready platforms.

You will build scalable offline and online inference pipelines, transform research prototypes into maintainable platform features, and drive cost-efficient deployments.

Qualifications

  • 5+ years of software engineering experience with deep expertise building and running production ML systems or model-backed distributed infrastructure at scale.
  • Hands-on mastery of deep learning model serving and inference optimisation, including GPU utilisation, dynamic batching, and latency-throughput-cost trade-offs.
  • Proven track record designing and operating scalable distributed systems on Kubernetes and cloud infrastructure (GCP/AWS) using Python and PyTorch.
  • Based in or able to relocate to London, working on-site in the office at least four days a week.

Responsibilities

  • Architect and run low-latency serving infrastructure for heavy vision and multimodal models, delivering real-time predictions directly into high-throughput annotation workflows.
  • Build scalable offline inference pipelines processing millions of hours of egocentric video for robotics customers, balancing GPU cluster costs, throughput, and fault tolerance.
  • Productionise agentic quality-control and active learning workflows, transforming research prototypes into resilient, self-healing platform features.
  • Profile and optimise end-to-end model serving performance across PyTorch, CUDA, and Kubernetes environments on AWS and GCP.

Skills

Software engineering
Deep learning serving
GPU optimization
Kubernetes
Python
PyTorch
Cloud infrastructure
Model deployment

Tools

PyTorch
CUDA
Kubernetes
AWS
GCP

Job description

Dex is seeking a highly experienced ML systems engineer to architect and operate real-time multimodal model serving at scale in London. You will own GPU utilisation, latency, and throughput optimisations across PyTorch, CUDA, Kubernetes on AWS/GCP, delivering robust production-ready platforms.

You will build scalable offline and online inference pipelines, transform research prototypes into maintainable platform features, and drive cost-efficient deployments.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Senior Machine Learning Engineer
Senior Machine Learning Engineer

Dex • Greater London

On-site
GBP 120,000 - 180,000
Senior ML Engineer: Real‑Time Vision Inference & Scale
Senior ML Engineer: Real‑Time Vision Inference & Scale

present of AI • Greater London

Hybrid
GBP 90,000 - 120,000
Senior ML Systems Engineer: Scale & Deploy Vision Models
Senior ML Systems Engineer: Scale & Deploy Vision Models

FDE Times • Greater London

On-site
GBP 90,000 - 150,000
Salary with equity
Strong in-person culture in London
25 days annual leave + UK holidays
+4
Senior ML Systems Engineer – Production Vision & Multimodal
Senior ML Systems Engineer – Production Vision & Multimodal

Encord • Greater London

On-site
GBP 90,000 - 140,000
Competitive salary
Equity in a high-growth startup
London office most days
+5
Principal ML Engineer - Real-Time AI Systems
Principal ML Engineer - Real-Time AI Systems

Boost Talent • Greater London

Hybrid
GBP 108,000 - 132,000
Senior ML Performance Engineer - Real-Time Inference & Scale
Senior ML Performance Engineer - Real-Time Inference & Scale

Odyssey • Greater London

On-site
GBP 70,000 - 90,000
Senior ML Engineer – Hybrid London (CUDA, PyTorch)
Senior ML Engineer – Hybrid London (CUDA, PyTorch)

Hexwired Recruitment Limited • Greater London

Hybrid
GBP 83,000 - 110,000
On-site Research Engineer, Multimodal Vision & 3D Robotics
On-site Research Engineer, Multimodal Vision & 3D Robotics

Dex • Greater London

On-site
GBP 90,000 - 150,000
Remote ML Engineer: PyTorch, NLP & CV
Remote ML Engineer: PyTorch, NLP & CV

trg. • Greater London

Hybrid
GBP 54,000 - 90,000
Staff ML Engineer (Python) — Real-Time pLTV & Growth
Staff ML Engineer (Python) — Real-Time pLTV & Growth

Dex • Greater London

On-site
GBP 198,000 - 242,000
Competitive compensation
Performance bonus
Strong influence over technical direction