Member of Technical Staff (AI Inference Engineer)

Highlights

• Build and run the inference engine behind every Perplexity query at scale.
• Support transformer, text-generation and multimodal models from loading to serving.
• Optimize latency and cost while keeping rapidly growing traffic reliable.

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-world impact.

Requirements

• 3+ years of professional software engineering experience 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
• Familiarity with at least one deep learning framework (PyTorch, JAX, TensorFlow)
• Understanding of GPU architectures, LLM architectures and inference optimization techniques
• Self-directed and comfortable owning problems end-to-end in fast-moving environments