Location: London | Type: Permanent
Salary: £80,000–£100,000 per annum
Role Summary Build and operate reliable infrastructure for a research and product platform handling CAD jobs, model training, simulations, and data pipelines. As an MLOps Infrastructure Engineer, you'll design systems that prevent experiments from becoming cost or reliability surprises, operating LLM serving pipelines, GPU infrastructure, and secure data storage at scale.
Key Responsibilities
- Build infrastructure for model serving, simulation jobs, and secure data storage.
- Operate LLM and robotics-model deployment pipelines in production.
- Implement CI/CD, observability, experiment tracking, and cost controls.
- Keep CAD, simulation, and model jobs reliable and performant.
- Design and maintain secure data pipelines supporting repeatable experiments.
- Support model evaluation workflows and reduce infrastructure cost while maintaining uptime.
- Monitor frontier API routing, GPU serving, and inference optimization.
- Strong proficiency with Docker, Kubernetes, and CI/CD pipelines.
- Hands-on experience with GPU serving and inference optimization.
- Knowledge of job queues, observability platforms, and experiment tracking systems.
- Solid understanding of cloud infrastructure (AWS, Azure, or GCP), secrets management, and security practices.
- Experience implementing cost control and performance monitoring.
- Familiarity with data storage solutions, model versioning, and deployment workflows.
- An MLOps Infrastructure Engineer with experience operating LLM serving infrastructure or robotics model pipelines is ideal.
- Background with CAD job scheduling or simulation workload optimization.
- Exposure to experiment tracking frameworks and ML model evaluation systems.
- Experience reducing infrastructure costs in ML/research environments.
- Knowledge of frontier model APIs and API routing strategies.
Candidate Profile
- Hands-on MLOps Infrastructure Engineer comfortable supporting research and product teams.
- Pragmatic problem-solver focused on reliability and cost efficiency.
- Able to work across multiple job types (models, simulations, data pipelines, CAD).
- Strong communication and collaboration skills.
- Proactive about monitoring, debugging, and preventing infrastructure surprises.
- Hands-on technical role with real infrastructure impact.
- Opportunity to optimize systems handling diverse workloads (ML, simulation, CAD).
- Exposure to cutting-edge research and product infrastructure challenges.
- Competitive salary and benefits.
- Fast-paced environment supporting innovation at scale.
Get in touch: max@neartechsearch.com
