Software Engineer Inference
SierraVisit Sierra website
Enterprise conversational-AI platform that helps businesses build and operate customer-experience agents across channels.
Maintainer signals as of 9/25/2026
San Francisco, United States
About Sierra
Sierra provides an AI platform for businesses to build, deploy, analyze, and optimize customer-facing agents across chat, SMS, WhatsApp, email, voice, and ChatGPT.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design and operate inference architecture across self-hosted models and third-party providers. You will build routing, failover, capacity, quota, and serving systems; run GPU infrastructure; and improve latency, reliability, throughput, and cost for production workloads.
Requirements
- Distributed systems
- Large-scale production systems
- Infrastructure architecture
- Latency optimization
- Reliability engineering
- Capacity management
- Cost optimization
Responsibilities
- Partner with frontier labs and inference providers
- Design inference traffic architecture across models and providers
- Build routing, failover, capacity management, and quota systems
- Build and operate self-hosted model inference on GPU infrastructure
- Optimize inference latency, throughput, and cost
- Make architectural decisions across hybrid inference infrastructure
- Tune serving engines and infrastructure with inference providers
- Contribute to post-training infrastructure
Benefits
- Unlimited paid time off
- Medical, dental, and vision benefits for employees and families
- Life insurance
- Disability benefits
- Retirement plan
- Parental leave
- Fertility and family-building benefits
- Lunch, snacks, and coffee
- Discretionary benefit stipend
- Free alphorn lessons
- Equity