About the role
At Sierra, a leader in customer-facing AI platforms, the engineering team focuses on building scalable systems that support real-time AI reasoning. The company works with major brands and emphasizes values like trust, craftsmanship, and customer obsession. The team is based in San Francisco, and the company fosters a culture of innovation and responsibility, working across North America, Europe, and Asia.
The role of a Software Engineer in Inference involves designing and maintaining systems that serve and route AI inference workloads efficiently. The engineer will collaborate with external inference providers, optimize for low latency and high reliability, and manage GPU infrastructure for self-hosted models. The position requires a strong background in distributed systems and large-scale infrastructure management.
Candidates should have experience with large-scale production systems, making architectural decisions, and operating complex infrastructure. Knowledge of ML infrastructure, inference frameworks, and GPU deployment is a plus. The role is onsite in San Francisco and involves working on cutting-edge AI infrastructure, with a focus on performance, reliability, and scalability.