Technical Lead, On-Device AI Inference

Location: San Jose, United States

Salary: $300,000–$500,000 annual base salary

Company

hirify.global is an artificial intelligence company developing personalized, proactive, multimodal intelligence and next-generation AI hardware.

What you will do

• Evaluate GPUs, NPUs, DSPs, and specialized accelerators for on-device model deployment.
• Co-design foundation model and audio ML architectures around latency, memory, and power constraints.
• Build low-level execution layers, custom kernels, runtime systems, and compiler paths for transformer workloads.
• Partner with silicon vendors and internal hardware teams to bring up new accelerators.
• Hire and lead engineers building performance-critical inference software.

Requirements

• 8–12+ years of experience in high-performance computing.
• Production experience deploying workloads on GPUs, NPUs, or specialized accelerators.
• Deep knowledge of attention, KV-cache behavior, quantization, and memory bandwidth limitations.
• Experience designing or optimizing inference engines, distributed runtimes, or ML compilers, including writing performance-critical kernels.
• Experience leading teams and setting technical direction for performance-critical software.
• Experience taking research models from checkpoints to constrained hardware used in a product.

Nice to have

• Experience with Hexagon DSP, Ambiq-class MCUs, or comparable embedded AI silicon.
• Experience with speech, audio, or streaming multimodal inference.
• Contributions to open-source inference or compiler toolchains such as TensorRT, ONNX Runtime, TVM, or MLIR.

Culture & Benefits

• Work on multimodal AI systems combining speech, text, vision, and persistent memory.
• Develop AI models and hardware together as a unified interface between humans and machines.
• Additional compensation components and benefits may be included depending on the role.