Lead Member of Technical Staff, Model Serving

Role Impact and Responsibilities:

• Lead the technical direction and architecture for scalable, reliable machine learning systems serving advanced NLP applications.
• Drive the design, deployment, and operation of the AI platform, ensuring high availability and performance for customer API endpoints.
• Mentor engineers and establish team-wide standards and best practices for complex, distributed systems.

Technical Environment and Challenges:

• Develop and optimize systems using Kubernetes and manage GPU workloads across large-scale, multi-cloud and hybrid serving environments.
• Own compute, storage, and network resource management at an organizational level, including cost optimization strategies.
• Solve and guide others through evolving technical challenges involving accelerators, distributed systems, and high-performance servers.

Candidate Profile and Requirements:

• Possess 8+ years of engineering experience with a track record of technical leadership in production infrastructure at scale.
• Demonstrate deep expertise in Kubernetes, cloud platforms (GCP, Azure, AWS), and the computational characteristics of accelerators like GPUs/TPUs.
• Show proficiency in languages like Golang or C++, with exceptional collaboration and communication skills for cross-functional initiatives.