Member of Technical Staff (ML Systems)

Location: San Francisco, CA; on-site

Salary: $150K–$350K per year, plus equity

Company

hirify.global is building a multi-silicon neocloud for fast, efficient AI inference across heterogeneous hardware.

What you will do

• Build and optimize production inference systems for latency, throughput, and efficiency.
• Design execution strategies for batching, scheduling, concurrency, and resource utilization.
• Improve KV cache management, memory efficiency, and runtime behavior at scale.
• Enable new model architectures and inference techniques to run efficiently in production.
• Partner with compiler, kernel, networking, and distributed systems engineers on end-to-end performance.
• Influence the architecture of a large-scale AI infrastructure platform.

Requirements

• Strong software engineering fundamentals.
• Experience building or operating ML inference or model-serving systems.
• Ability to reason about performance, memory usage, and system behavior under load.
• Bachelor's degree in a relevant field, or equivalent education, training, and professional experience.
• Software development experience in Python and C++.

Nice to have

• Experience with TensorRT-LLM, vLLM, or custom serving systems.
• Deep understanding of modern model architectures and attention mechanisms.
• Experience with batching, scheduling, concurrency control, KV cache management, and memory placement.
• Experience profiling and tuning latency- and throughput-critical systems.

Culture & Benefits

• Early-stage environment with significant ownership over technical work.
• Direct collaboration with a small group of highly capable colleagues.
• Opportunity to work across domains and help shape the company's architecture and growth.
• Equity offered as part of compensation.