Inference Engineering, Co-op

The role

Co-op students will work on systems that determine how fast, efficiently, and reliably frontier AI models run on frontier workloads at scale. You will work on the vLLM stack, including model execution, low-level accelerator code, distributed serving, or the cloud platform.

What you will do

• Implement ideas from research papers for inference techniques
• Support mixture-of-experts, multimodal, diffusion, and agentic workloads
• Improve scheduling, continuous batching, KV-cache memory management, prefix caching, and hybrid model serving
• Build the distributed serving data plane for running across many GPUs and nodes
• Work on tensor, expert, or context parallelism
• Write and optimize attention, GEMM, sampling, KV-cache, fused, and quantization kernels
• Help make vLLM first-class on AMD accelerators
• Build backend, runtime, and compiler integrations with JAX, XLA, Pallas, and MLIR
• Build the operational platform for large-scale inference deployment
• Work on Kubernetes and custom operators

Required qualifications

• Currently pursuing a bachelor's, master's, or PhD degree in computer science, engineering, mathematics, or a related technical field
• Eligible for a University of Waterloo co-op work term
• Strong programming ability in Python, C++, Rust, Go, or another systems-oriented language
• Strong computer science fundamentals and the ability to learn from research papers, technical documentation, and complex systems code
• Evidence that you have built and debugged nontrivial software through coursework, research, a prior internship, open-source work, or an ambitious side project
• A builder mindset

Nice to have

• Depth in at least one relevant area such as ML or inference systems, distributed systems, GPU or accelerator programming, compilers, high-performance computing, operating systems, networking, Kubernet
• Hands-on experience with one or more relevant technologies such as PyTorch, vLLM, SGLang, TensorRT-LLM, CUDA, Triton, TileLang, ROCm/HIP, JAX/XLA, Pallas, Kubernetes, Helm, Terraform, Ray, or SLURM
• Experience profiling or benchmarking software, validating numerical or systems correctness, or building tests that protect against performance regressions
• Experience with systems beyond a single local process or device, including multi-GPU, multi-node, research-cluster, high-throughput, or production-like workloads
• Contributed to open-source ML, systems, compiler, or infrastructure projects, especially vLLM or adjacent projects
• Built a research system, benchmark suite, compiler or kernel project, distributed service, or infrastructure tool that demonstrates unusual technical depth and initiative
• Worked across more than one layer of the stack and enjoy moving between algorithms, runtimes, systems, and hardware

Benefits

• Competitive compensation based on the applicable co-op market and candidate background
• Housing stipend for the duration of the co-op term

Before you apply

• Must be eligible for a University of Waterloo co-op work term

About the company

Inferact's mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper and faster. Founded by the creators and core maintainers of vLLM, the company sits at the intersection of models and hardware.