Staff Software Engineer (Inference Platform), London
Isomorphic Labs
Overview
In this role you will lead the reliability and scale of IsoLabs' foundation-model platform, collaborating with research and Applied ML teams to support larger models and data volumes. You will design and implement robust infrastructure, from GPU/TPU workloads to inference services, while improving observability and CI/CD stability. Your work enables researchers to run at digital speed with high throughput and minimal friction. This position offers a chance to shape biotech AI foundations and contribute to disease-focused innovation.
Pay / Benefits- hybrid working model
- 3 days in the office per week
- collaborative culture
- disability accommodation discussions
- equal employment opportunities
- learning and growth culture
- Own end-to-end platform reliability strategy for accelerator infrastructure and workload orchestration
- Lead reliability work for the global job scheduler
- Design a robust test harness to validate infrastructure upgrades safely
- Architect and optimize next-generation inference services for high throughput
- Overhaul logging and monitoring for proactive failure detection
- Improve internal CI/CD stability and faster feedback loops
- Contribute to tooling and architectural decisions across science, product, and operations teams
- Proven experience architecting and managing large-scale AI/ML workloads in production
- Expertise in cloud compute design within Google Cloud Platform (GCP)
- Significant experience deploying and managing workloads with Kubernetes (GKE)
- Professional familiarity with NVIDIA GPU generations and high-performance compute
- Strong programming skills and a reliability-first software development mindset
- Cross-functional collaboration
- Stakeholder management in fast-paced environments
- Curiosity and rigorous problem solving
- Google Cloud Platform (GCP)
- Kubernetes (GKE)
- NVIDIA GPUs
Reference: WJ-747_31165221