Member of Technical Staff (AI Inference Engineer)

📋 Description

• We build and run the inference engine behind every Perplexity query and deploy dozens of model
• Our stack is Rust, Python, CUDA, and CuTe DSL.
• Join a team focused on high-performance ML inference systems in production.

🎯 Requirements

• Deep experience with GPU programming and performance work (CUDA, Triton, CUTLASS, or similar).
• Understand modern LLM architectures and production deployment.
• Experience building/operating production distributed systems under real load.
• Comfort with Rust for serving runtime, Python for model code, CUDA/CuteDSL for kernels.
• Ability to read research papers, implement kernels, and troubleshoot production incidents.
• Self-directed in fast-moving environments.

🎁 Benefits

• Equity
• Competitive compensation with salary range disclosed