Software Engineer, Inference - Performance Optimization (AI)

TL;DR

Software Engineer, Inference - Performance Optimization (AI): Building and optimizing the inference stack across application, model, and fleet layers with an accent on reducing latency and cost-to-serve. Focus on developing high-fidelity performance models, identifying system bottlenecks, and optimizing hardware efficiency.

Location: San Francisco, USA

Salary: $295K – $555K + Equity

Company

hirify.global is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.

What you will do

• Build and refine performance models that translate microbenchmark results into cost-to-serve estimates.
• Analyze end-to-end inference workloads across applications, models, and fleet infrastructure.
• Enhance tooling to identify bottlenecks across layers for latency and throughput.
• Partner with cross-functional teams to turn performance insights into concrete improvements.
• Project how future architectural changes affect inference performance and capacity.

Requirements

• Deep expertise in performance profiling, benchmarking, analysis, and optimization.
• Strong ability to reason from first principles about distributed systems and model inference.
• Experience working across abstraction layers, from application behavior to kernels, accelerators, and networking.
• Knowledge of fleet scheduling and hardware efficiency.
• Must be based in or authorized to work in the US (San Francisco).

Culture & Benefits

• Opportunity to work at the forefront of AI research and deployment.
• Competitive compensation package including base salary and equity.
• Collaborative environment working with world-class engineering and research teams.
• Commitment to safety and human-centric AI development.