Design, deploy, and manage ML infrastructure on AWS and Kubernetes. Build scalable pipelines for LLM and video generation models. Collaborate with ML teams to productionize new models.
Key Highlights
Technical Skills Required
Benefits & Perks
Job Description
AI Infrastructure Engineer - Fully Remote (UK-based) | Salary: £50,000-£60,000
FRESH has partnered with an AI‑driven startup who are building software that translates written/spoken English into sign language. By combining AI, computer vision and sign‑language expertise they're able produce realistic sign‑language interpreters and integrate them into sites, videos and real‑world systems.
We’re looking for an AI Infrastructure Engineer to build and scale the systems behind the AI video generation and LLM models. You’ll work at the intersection of machine learning and cloud infrastructure, ensuring our models run efficiently, reliably, and cost-effectively at scale.
Key Responsibilities
- Design, deploy, and manage ML infrastructure on AWS (SageMaker) and Kubernetes
- Build scalable pipelines for LLM and video generation models
- Optimise model inference, latency, and costs
- Implement monitoring, logging, and alerting for production systems
- Collaborate with ML teams to productionize new models
- Manage compute scaling, security, and compliance
- Develop automation and tooling for smoother ML operations
Skills & Experience
- Strong Python skills and production coding experience
- Proven experience deploying/scaling LLMs or generative AI models
- Knowledge of GPU optimization and distributed training
- Expertise in AWS SageMaker, Kubernetes, and CI/CD (Terraform/CloudFormation)
- Solid understanding of ML serving, optimisation, and cloud architecture
Nice to Have:
Video generation or computer vision experience, model compression, distributed training, and familiarity with tools like Prometheus, Grafana, CloudWatch.
Benefits
- Fully remote (UK)
- Stock Options
- Free sign language classes
- Work with cutting-edge AI technology