Job Description
Infrastructure‑focused role on Perplexity’s AI team, responsible for large‑scale deployment and optimization of LLM inference (Python/Rust/C++, PyTorch, Triton, CUDA, Kubernetes), building APIs and platforms that serve real‑time queries for the answer engine and agents.
Responsibilities
- Develop and maintain APIs for AI inference used by internal teams and external customers.
- Benchmark and resolve bottlenecks across the inference stack (compute, networking, batching, caching).
- Improve reliability and observability of inference systems and participate in incident response.
- Implement cutting‑edge LLM inference optimizations informed by current research.
Benefits
Cash compensation range of $190,000–$250,000 plus equity.Comprehensive health, dental and vision insurance for employees and dependents, including a 401(k) plan.Hybrid work centered on the San Francisco Bay Area office.
Category
MLOps / AI Infrastructure
Posted
11/5/2025