Member of Technical Staff (AI Inference Engineer)

Highlights

• Build and run the inference engine behind every Perplexity query at scale.
• Bring up retrieval, text-generation and multimodal models in production.
• Build dashboards and automated remediation to catch regressions early.

What they offer

• Equity
• Health insurance
• Dental insurance
• Vision insurance
• Retirement benefits
• Fitness benefits
• Commuter benefits
• Dependent care accounts

Ideal candidate

A self-directed systems thinker who owns problems end-to-end and thrives in fast-moving environments. You love squeezing performance from GPUs and running critical production systems under real load.

Requirements

• 3+ years of professional software engineering with ML inference or high-performance systems
• Deep experience with GPU programming and performance work
• Understanding of modern LLM architectures and reliable production deployment
• Built and operated production distributed systems under real load
• Comfortable working across languages and layers from runtime to kernels
• Familiarity with at least one deep learning framework (PyTorch, JAX, TensorFlow)
• Understanding of GPU architectures including memory hierarchy and tensor cores
• Understanding of LLM inference optimization like quantization and speculative decoding
• Self-directed ownership with end-to-end problem solving in fast-moving environments