Architect, Inference Optimization & GPU Performance

Venice; Sheridan (WY); On-site; USD 150,000 - 230,000; Full time

Job summary

Venice is hiring a senior performance optimization leader to own the inference performance strategy and to recruit and lead the Inference Optimization Team. You will optimize GPU infrastructure across architectures, improve latency and throughput for large language model workloads, and build benchmarks to identify the best engines and quantization schemes.

You’ll evaluate new techniques and hardware viability, shaping Venice's high‑scale AI stack.

Qualifications

• 8+ years in performance optimization or HPC
• Strong GPU architecture and parallel programming knowledge
• Experience leading engineering teams
• Hands-on with production LLM inference engines and CUDA/C++ is a plus

Responsibilities

• Own Venice’s inference performance strategy
• Lead the Inference Optimization Team
• Optimize GPU infrastructure across architectures
• Improve latency, throughput, and cost per token for LLM inference
• Build benchmarking harnesses across inference engines
• Work with inference routing to optimize load‑balancing
• Evaluate new optimization techniques and hardware viability

Skills

GPU architecture

Performance optimization

Team leadership

Python

Rust/Go

CUDA/C++

Tools

Nsight Systems

Nsight Compute

PyTorch Profiler

Job description

Venice is hiring a senior performance optimization leader to own the inference performance strategy and to recruit and lead the Inference Optimization Team. You will optimize GPU infrastructure across architectures, improve latency and throughput for large language model workloads, and build benchmarks to identify the best engines and quantization schemes.

You’ll evaluate new techniques and hardware viability, shaping Venice's high‑scale AI stack.