Member of Technical Staff — Model Optimization and Inference (Experienced)

Location: In-person in Seattle, Washington, five days a week

Salary: $250,000–$350,000 base salary per year, plus equity

Company

hirify.global is a research company building photorealistic, real-time AI avatars with emotional intelligence through full-duplex audiovisual foundation models.

What you will do

• Own end-to-end inference optimization across LLM, audio, and diffusion model stacks.
• Implement KV cache strategies for long-context conversations, including eviction, compression, and memory-efficient attention.
• Evaluate, deploy, and extend vLLM, SGLang, TensorRT-LLM, and similar inference serving frameworks.
• Profile and benchmark latency and throughput, systematically identifying and eliminating bottlenecks.
• Build profiling viewers, inference test harnesses, and internal tooling for rigorous optimization.
• Accelerate diffusion inference and apply quantization, custom kernels, batching, and other inference-time optimization techniques.

Requirements

• Significant hands-on experience optimizing LLM inference in production or high-traffic research environments.
• Proficiency with vLLM, SGLang, TensorRT-LLM, or similar frameworks, including adapting non-default configurations to specialized workloads.
• Experience optimizing diffusion model inference through latency reduction, step distillation, caching, or kernel-level work.
• Strong Python and PyTorch skills, with a systematic measure-first approach to profiling and optimization.
• Experience with KV caching, memory layout, attention kernels, batching strategies, or speculative decoding.
• Visa sponsorship is available from day one, including O-1, H-1B, and green card sponsorship.

Nice to have

• Experience with post-training quantization such as GPTQ or AWQ.
• Familiarity with multimodal or streaming inference architectures.
• Experience deploying real-time AI systems with hard latency SLAs.
• Experience at an AI lab, inference startup, or high-traffic model serving platform.
• Open-source contributions to inference frameworks.

Culture & Benefits

• Small research-focused team working on unsolved real-time AI problems.
• AI-native tooling and access to advanced development tools.
• HSA health plan with approximately $2,000 in annual company contributions.
• 15 days of PTO, public holidays, and a full week of office closure at year-end.
• Weekday meals, drinks, snacks, commuter benefits, and a 401(k) plan.