1 month ago
Base Salary
$230k - $390k/yr
Responsibilities
- Partner with frontier labs and inference providers to secure capacity and coordinate training and inference infrastructure.
- Design Sierra’s inference architecture across models, infrastructure, providers, serving layers, and proxy layers.
- Build routing, failover, capacity-management, and quota systems for low-latency, reliable production inference.
- Operate self-hosted inference on GPU infrastructure, including containers, inference engines, and compute capacity.
- Optimize inference latency, throughput, reliability, and cost through serving-engine and infrastructure improvements.
- Contribute to post-training infrastructure and collaborate with the Models and Agent Runtime teams.
Requirements
- Demonstrated deep systems thinking and strong distributed-systems fundamentals.
- Experience designing, building, operating, and owning large-scale production systems from architecture through operation.
- Strong judgment in balancing latency, reliability, capacity, and cost.
- Ability and enthusiasm to apply systems expertise to evolving AI infrastructure.
- Preferred experience with ML infrastructure, MLOps, production inference systems, large-scale LLM serving, self-hosted inference, GPU infrastructure, post-training infrastructure, or inference-performance optimization.
- Familiarity with inference frameworks such as vLLM or SGLang.
Benefits
- Flexible unlimited paid time off.
- Medical, dental, vision, life insurance, and disability benefits for employees and families as applicable.
- Retirement plan dependent on country of employment.
- Parental leave and fertility and family-building benefits through Carrot.
- Lunch, snacks, coffee, and free alphorn lessons.
- Discretionary benefit stipend and eligibility to participate in equity plans.
- Primarily in-person work based in San Francisco, with offices across North America, Europe, and Asia.
Categories
About Sierra
Sierra builds an enterprise conversational AI platform that powers customer service and other customer-facing interactions for large organizations. The company sells SaaS and deployed solutions that integrate with enterprise systems and meet security and compliance requirements. Headquartered in San Francisco with offices across North America, Europe, and Asia-Pacific, Sierra was co-founded by Bret Taylor and Clay Bavor, longtime leaders at Salesforce, Facebook, and Google.