3 hours ago
Base Salary
$230k - $390k/yr
Responsibilities
- Design Sierra’s inference architecture across models, infrastructure, and third-party providers.
- Build serving, proxy, 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 speculative-decoding techniques.
- Partner with frontier labs, inference providers, Applied Research, Models, and Agent Runtime teams.
- Contribute to infrastructure supporting the broader model lifecycle, including post-training.
Requirements
- Deep systems thinking and strong distributed-systems fundamentals.
- Experience designing, building, and operating large-scale production systems.
- Strong judgment regarding latency, reliability, capacity, and cost tradeoffs.
- Experience owning complex infrastructure from architecture through production operation.
- Ability and enthusiasm to apply systems expertise to AI infrastructure and learn quickly.
- 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, and vision benefits for employees and families.
- Life insurance, disability benefits, and a retirement plan dependent on country of employment.
- Parental leave and fertility and family-building benefits through Carrot.
- Lunch, snacks, and coffee provided.
- Discretionary benefit stipend.
- Free alphorn lessons.
- Full-time employees may participate in equity plans subject to applicable policies.
- Primarily in-person role 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.