Senior Performance Engineer (AI Inference)

Location: Headquarters/Sunnyvale Office; on-site

Company

hirify.global builds large-scale AI hardware and inference systems designed to deliver significantly higher training and inference speeds than GPU-based platforms.

What you will do

• Build, run, and maintain reproducible inference benchmarks for code generation, summarization, multi-turn conversation, and agentic tool use.
• Measure tokens per second, time to first token, latency under concurrency, and total cost of ownership for real customer workloads.
• Evaluate inference optimization techniques including kernel fusions, flash-attention variants, quantization, and GPU memory strategies.
• Build and continuously update competitive pricing models covering token-based, throughput-based, and enterprise contract pricing.
• Prepare competitive analyses and actionable briefs for Sales, Product, Engineering, executives, and sales leaders.
• Track third-party benchmarking sources and ensure hirify.global performance is accurately represented.

Requirements

• Deep practical experience with open-source inference frameworks such as vLLM, SGLang, or TensorRT-LLM.
• 5+ years of experience in ML systems, ML research engineering, or high-performance computing.
• Strong understanding of LLM inference economics, including tokens, throughput, latency, batch sizes, precision trade-offs, and customer cost.
• Strong understanding of transformer architecture internals, including attention mechanisms and KV-cache management.
• Self-directed and resourceful approach to technical research and analysis.

Nice to have

• ML research background with publications or significant open-source contributions focused on systems or efficiency.
• Contributions to open-source inference or kernel optimization projects.
• Excellent communication skills for collaborating with executives, engineers, and sales leaders.

Culture & Benefits

• Opportunity to build an AI platform beyond the constraints of GPUs.
• Access to cutting-edge AI research and opportunities to publish or open source work.
• Work with one of the fastest AI supercomputers in the world.
• Job stability combined with startup vitality.
• Non-corporate work culture focused on individual beliefs, learning, growth, and support.