Inference Architecture Interns (AI)

Location: On-site at the office in San Jose, CA

Compensation: Paid 12-week internship

Company

hirify.global builds hardware, software, racks, and manufacturing systems for frontier AI inference.

What you will do

• Port state-of-the-art models to the company’s inference architecture and build programming abstractions and testing capabilities.
• Build and scale runtime systems for multi-node inference, intra-node execution, state management, and error handling.
• Optimize routing and communication layers using collectives.
• Use performance profiling and debugging tools to identify bottlenecks and correctness issues.
• Co-design hardware instructions and model operations to maximize inference performance.
• Implement high-performance software components for the Model Toolkit.

Requirements

• Progress toward a Bachelor’s, Master’s, or PhD in computer science, computer engineering, applied mathematics, or a related field.
• Proficiency in Python and C++.
• Understanding of performance-sensitive or complex distributed software systems, Linux internals, accelerator architectures, compilers, or high-speed interconnects.
• Experience porting applications to non-standard accelerator hardware or platforms.
• Deep knowledge of transformer architectures and/or inference serving stacks such as vLLM or SGLang.

Nice to have

• Proficiency in Rust.
• Experience with low-latency, high-performance networking, distributed systems, SIMD optimization, PyTorch, or JAX.
• Knowledge of Mixture-of-Experts transformer architectures or experience in math competitions.

Culture & Benefits

• Fully in-person work with direct mentorship from experienced engineers and industry leaders.
• Generous housing support for those relocating.
• Daily lunch and dinner at the office.
• Opportunity to work across engineering and research disciplines on frontier AI infrastructure.