Senior ML Systems Engineer – Vision & Inference (Equity)

Encord; Greater London; On-site; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Competitive salary

Meaningful equity

London office culture

Learning & development budget

Travel for customer visits across the

Job summary

Encord is seeking a Senior ML Systems Engineer to join our in-house ML team in London. You will design, build and operate model-serving and inference infrastructure for transformer-based vision and multimodal models, focusing on latency, throughput, reliability and GPU cost.

You will own the serving architecture behind core ML features, collaborate with research and product engineering, and turn prototypes into production-ready features.

Qualifications

• 5+ years of software engineering experience with production ML systems
• Ability to design scalable, reusable architectures for ML features
• Strong collaboration across research, product, and engineering
• Bridge between research and production with hands-on delivery experience
• Experience deploying modern deep learning models in production and optimizing for latency, throughput, and GPU cost

Responsibilities

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

Skills

Python

Software engineering

System design

ML systems

Production deployment

Collaboration

Research-to-production bridge

Distributed systems

Problem solving

Communication

Tools

PyTorch

CUDA

Kubernetes

GCP

AWS

Job description

Encord is seeking a Senior ML Systems Engineer to join our in-house ML team in London. You will design, build and operate model-serving and inference infrastructure for transformer-based vision and multimodal models, focusing on latency, throughput, reliability and GPU cost.

You will own the serving architecture behind core ML features, collaborate with research and product engineering, and turn prototypes into production-ready features.