Senior ML Systems Engineer – Production Vision & Multimodal

Encord; Greater London; On-site; GBP 90,000 - 140,000; Full time

Benefits offered by this job

Competitive salary

Equity in a high-growth startup

London office most days

25 days annual leave

Learning & development budget

Travel for customer visits across the.

Daily company lunches

Team offsites

Job summary

Encord is looking for a Senior ML Systems Engineer to join our in-house ML team in London. You will design, build and operate the infrastructure that serves our computer vision and multimodal models in production, transforming prototypes into reliable features within a GPU-focused, scalable platform.

You will work across research and engineering, collaborating with Product Engineering and Human Data teams to push ML-driven workflows from prototype to shipped product.

Qualifications

• 5+ years of software engineering experience including ML systems in production
• Strong software engineering and system design fundamentals
• Hands-on experience deploying modern deep learning models in production
• Experience designing and operating scalable distributed production systems with GPU workloads
• Ability to reason end-to-end about data, models, evaluation, deployment and retraining
• Track record of owning complex systems from design to production
• Bonus: CV or multimodal deployment experience, or model-serving frameworks

Responsibilities

• Design, build and operate model-serving and inference infrastructure for transformer-based vision and multimodal models
• Own the serving architecture behind ML features, balancing latency, throughput and GPU cost
• Optimize models and pipelines for production via batching, caching, and orchestration
• Integrate models into Encord's product and annotation workflows
• Build reusable abstractions across models and data types
• Set up monitoring and observability and own reliability of live features
• Turn prototypes into shipped features in production
• Contribute to platform design decisions and participate in design reviews

Skills

System design

Distributed production systems

ML deployment

Performance optimisation

Cross-functional collaboration

Tools

Python

PyTorch

CUDA

Kubernetes

GCP

AWS

Job description

Encord is looking for a Senior ML Systems Engineer to join our in-house ML team in London. You will design, build and operate the infrastructure that serves our computer vision and multimodal models in production, transforming prototypes into reliable features within a GPU-focused, scalable platform.

You will work across research and engineering, collaborating with Product Engineering and Human Data teams to push ML-driven workflows from prototype to shipped product.