Requirements

• 5+ years of software engineering experience, including building and operating ML systems or model-backed products in production at scale
• Strong software engineering and system design fundamentals
• Hands-on experience deploying modern deep learning models in production with understanding of model serving, inference optimization, GPU utilization, and performance trade-offs
• Experience designing and operating scalable, distributed production systems, ideally involving GPU workloads, high-throughput data processing, or low-latency inference
• Ability to reason through an ML system end to end, from data and model choices to offline and online evaluation, deployment, monitoring, and retraining
• Track record of personally owning complex systems from design through to production

Nice to haves

• Computer vision or multimodal deployment experience
• Experience with model-serving frameworks
• Experience working with video, 3D, or other complex data types

What you'll be doing

• 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, reliability, and GPU cost
• Optimize models and pipelines for production through batching, KV caching, GPU utilization, and orchestration
• Integrate models into Encord's product and annotation workflows alongside Product Engineering
• Build reusable abstractions that cover multiple models, data types, customers, and evolving task templates
• Set up monitoring and observability, owning performance and reliability post-launch
• Transform prototypes from research teammates into shipped features
• Contribute to platform design decisions, participate in design reviews, and assist in hiring
• Work with Python, PyTorch, CUDA, Kubernetes, and GCP/AWS technologies

Perks and benefits

• Competitive salary and meaningful equity in a high-growth startup
• Strong in-person culture with most of the team working from the London office 4+ days per week
• 25 days of annual leave plus UK public holidays
• Annual learning and development budget
• Travel opportunities for customer visits, events, and conferences across the UK and Europe
• Daily company lunches
• Monthly socials and bi-annual team offsites