Member of Technical Staff - Inference

Ghost • San Francisco, CA

4d • Onsite

About The Position

Ghost is a personal AI hardware company building devices and software designed to make AI more capable and personal while giving people greater control over their time, attention, and goals. The Member of Technical Staff - Inference will build and optimize the inference stack that runs personal AI models locally on Core. The role focuses on improving latency, throughput, and memory efficiency for interactive requests and background agent workloads, profiling performance across hardware and software, and collaborating with hardware, post-training, and product teams. This position is on-site in San Francisco.

Requirements

• Experience building or optimizing inference systems for language models.
• Strong systems programming skills in C++ or similar languages, alongside proficiency in Python.
• Familiarity with GPU architecture, memory management, and performance profiling.
• Experience with inference runtimes, quantization, or GPU kernel development using CUDA, Triton, or equivalent tools.
• Strong experimental judgment and ability to identify bottlenecks and evaluate tradeoffs between speed, memory, power, and model quality.
• Ability to work on-site in San Francisco.

Responsibilities

• Build and optimize the inference stack that runs personal AI models locally on Core.
• Improve latency, throughput, and memory efficiency across interactive requests and background agent workloads.
• Profile performance across the hardware and software stack, optimizing kernels, memory movement, and runtime execution.
• Build benchmarks reflecting real product workloads, including long contexts, concurrent agents, and sustained operation.
• Work closely with the hardware, post-training, and product teams.

What This Job Offers

• Job Type: Full-time
• Education Level: No Education Listed