Staff Software Engineer (Inference Platform)
Posted Updated 2
views
Description
You will develop and operate an inference platform serving machine-learning models to scientific applications. You will define platform strategy and roadmaps, architect and optimize inference services, address scaling limits, contribute to tooling and architecture decisions, and deliver tested user-focused features.
Responsibilities
- Develop and operate an inference platform serving machine-learning models to scientific applications
- Design platform strategy and build roadmaps
- Architect and optimize next-generation inference services
- Solve scaling limits and ensure high-throughput performance and feature parity across the model-serving stack
- Contribute to technical decisions on tooling and architectural design
- Partner with science, product, and operations stakeholders to align infrastructure with biotech R&D cycles
- Deliver high-quality, well-tested, user-focused features
Requirements
- Proven experience architecting and managing large-scale AI and ML workloads in a production environment
- Significant experience deploying and managing complex workloads within Kubernetes and GKE
- Expertise in cloud compute design within Google Cloud Platform
- Professional familiarity with NVIDIA GPU generations and high-performance compute
- Strong programming skills and a reliability-first approach to software development
Skills
Sign in to read and join the discussion.