Member of Technical Staff, Inference Systems

Job overview

The Member of Technical Staff, Inference Systems is an onsite role in Palo Alto, CA, five days per week. Compensation is $230,000–$350,000 per year, plus competitive equity. The confidential client is building a high-performance AI inference platform from the ground up.

What you'll do

• Build an inference runtime in Rust, including batching, scheduling, request routing, and serving
• design KV cache management and prefix caching
• scale serving across GPUs and nodes
• profile and benchmark the inference pipeline
• ship performance improvements
• make architecture decisions with the founding team.

What we're looking for

Skills & competencies

member of technical staff

inference systems

palo alto ca

ai inference

rust

systems engineering

gpu scaling

kv cache

vllm

sglang

tensorrt-llm

$230k–$350k

visa sponsorship

Work arrangement

• Weekend coverage required

Benefits & perks

• Competitive equity.

Why this role

The posting seeks two or more years of systems engineering experience, deep knowledge of inference internals, experience with inference engines such as vLLM, SGLang, or TensorRT-LLM, and strong systems programming skills. Visa transfers and new H-1B and TN sponsorship are offered.

About the employer

Transparent Search Group is hiring for this role. Industry: Custom Computer Programming Services. Sector: 54.