Inference Infrastructure Engineer Intern (AI)

Location: Mountain View, United States

Company

hirify.global develops generalist intelligent robots across hardware, robot systems, infrastructure, foundation world models, and manufacturing.

What you will do

• Profile and benchmark inference for large video and world models to identify latency, throughput, and memory bottlenecks.
• Evaluate and implement inference optimization techniques including quantization, low-precision inference, distillation, sampling acceleration, attention and caching optimizations, model compilation, and graph-level optimization.
• Improve video decoding and preprocessing, input pipelines, host-device transfer, caching, and storage or I/O paths supporting inference and training.
• Write and tune performance-critical GPU kernels using CUDA, Triton, or similar technologies and integrate them into the inference stack.
• Build benchmarking and regression-tracking tools, and work with researchers to deliver production-quality infrastructure.
• Own a scoped, high-impact project end to end, ship it into a production or research workflow, and present the results.

Requirements

• Currently pursuing a BS, MS, or PhD in Computer Science, Electrical or Computer Engineering, or a related field.
• Strong programming skills in Python and/or C++.
• Solid understanding of deep learning fundamentals and at least one framework, preferably PyTorch.
• Comfort reading performance data and reasoning about latency, throughput, memory, and accuracy trade-offs.
• Strong depth in at least one area: ML inference optimization; data efficiency optimization for high-bandwidth data such as video; or GPU kernel optimization using CUDA, Triton, CUTLASS, or similar technologies.
• For GPU optimization, familiarity with GPU memory hierarchy, occupancy, and profiling tools such as Nsight Systems, Nsight Compute, or PyTorch Profiler.

Nice to have

• Experience with video model inference, including video generation, video diffusion, world models, or real-time video understanding pipelines.
• Research experience in systems or ML, including publications or substantial projects in venues such as MLSys, OSDI/SOSP, CVPR/ICCV, NeurIPS/ICML/ICLR, or similar.
• Experience with real-time or latency-critical inference on robots or edge and embedded accelerators.
• Experience with multi-GPU inference, including tensor, sequence, or pipeline parallelism.
• Contributions to open-source ML systems projects.

Culture & Benefits

• Work with infrastructure and research engineers on generalist robotics and real-world robot control.
• Mentorship from experienced infrastructure and research engineers.
• Access to modern GPU compute for experiments.