Member of Technical Staff (AI Inference Engineer)

Highlights

• Run the inference engine powering every Perplexity query at scale.
• Deploy dozens of model architectures under tight latency and cost budgets.
• Build dashboards and automated remediation to catch regressions early.

What they offer

• Equity

Ideal candidate

Self-directed systems builder who owns problems end-to-end and thrives in fast-moving environments. You care about low-latency, reliable production systems and turning research ideas into real user impact.

Requirements

• 3+ years professional software engineering with ML inference or high-performance systems
• Deep experience with GPU programming and performance work
• Understand modern LLM architectures and bring them up reliably in production
• Built and operated production distributed systems under real load
• Comfortable working across Rust, Python and CUDA/CuTe DSL layers
• Familiarity with PyTorch, JAX or TensorFlow
• Understanding of GPU architectures including memory hierarchy and tensor cores
• Understanding of LLM inference optimization like quantization and speculative decoding