Inference Engineering, Co-op

Inferact
San Francisco, CA
On-siteCareer-pivot friendly

Who this role is best for

Geared toward University of Waterloo co-op students comfortable with real engineering problems in AI inference systems.

Best fit for

  • University of Waterloo co-op students with strong systems programming skills and interest in AI inference systems
    — “We're looking for exceptional University of Waterloo co-op students”
  • Candidates with a builder mindset who can define success and iterate until a system works
    — “A builder mindset: you define what success means, measure results, validate correctness”
  • Individuals who enjoy working across multiple layers of the AI stack and solving complex problems
    — “Work across models, compilers, accelerators, networking, and distributed systems”

Things to consider

  • The role is not suitable for candidates without eligibility for a Waterloo co-op term
    — “Currently pursuing a bachelor's, master's, or PhD degree ... eligible for a University of Waterloo co-op work term”
  • Candidates should be prepared for a high degree of technical ownership and measurable contributions
    — “meaningful ownership, and mentorship from a small, senior team”

How to stand out

  • Highlight your experience in building and debugging nontrivial software on your resume
    — “Evidence that you have built and debugged nontrivial software”
  • Showcase any prior work in ML, compilers, or distributed systems with specific technical depth
    — “Depth in at least one relevant area such as ML or inference systems”
  • Emphasize any contributions to open-source projects, especially in ML or systems domains
    — “Contributed to open-source ML, systems, compiler, or infrastructure projects”
  • Demonstrate your ability to work with research papers and complex systems code
    — “ability to learn from research papers, technical documentation, and complex systems code”
  • Include experience with profiling, benchmarking, or validating software correctness
    — “Experience profiling or benchmarking software, validating numerical or systems correctness”
Pace · SteadyCollaboration · HighAutonomy · MediumDecision Impact · Company

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

  • Contribute to vLLM stack
  • Implement new model architectures
Typical background
University of Waterloo co-op studentExperience in AI inference

Skills & requirements

Required

Inference EngineeringAI ModelsDistributed Systems

Preferred

CUDATritonKubernetes

About the role

Original posting from Inferact via Ashby

Overview

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, we sit at the intersection of models and hardware, a position that took years to build.

About the Role

We're looking for exceptional University of Waterloo co-op students who want to work on the systems that determine how fast, efficiently, and reliably frontier AI models run on frontier workloads at scale. This is not a sandboxed internship project. We will match your strengths and interests to a real engineering problem across the vLLM stack, from model execution and low-level accelerator code to distributed serving and the cloud platform that makes it all usable.

You'll work alongside the creators and core maintainers of vLLM on work intended to ship into open source, production systems, or the tooling that supports both. You will have a primary technical track, meaningful ownership, and mentorship from a small, senior team, with opportunities to collaborate across models, compilers, accelerators, networking, and distributed systems. The goal is to let exceptional students learn at the frontier while making contributions used by developers and AI teams around the world.

Potential Focus Areas

Your co-op will have a primary home in one of the following tracks, with opportunities to contribute across others:

  • Inference Runtime: Bring new model architectures and inference techniques to life in vLLM. Implement ideas from research papers; support mixture-of-experts, multimodal, diffusion, and agentic workloads; and improve scheduling, continuous batching, KV-cache memory management, prefix caching, and hybrid model serving.
  • Performance & Scale: Build the distributed serving data plane that lets vLLM run across many GPUs and nodes. Work on tensor, expert, or context parallelism; prefill/decode separation and KV-cache transport; fault tolerance and multi-tenancy; and high-performance communication using NCCL, DeepEP, NVSHMEM, RDMA, or InfiniBand.
  • Kernel Engineering: Raise the hardware performance ceiling by writing and optimizing attention, GEMM, sampling, KV-cache, fused, and quantization kernels. Use CUDA, Triton, TileLang, CUTLASS/CUTE, or related tools; reason about memory hierarchy, occupancy, and tensor cores; and prove speedups through profiling, correctness tests, and reproducible benchmarks.
  • AMD GPU Performance: Help make vLLM first-class on AMD accelerators. Work across ROCm, HIP, Triton, CK, AITER, kernels, runtime paths, quantization, compiler integration, and performance-regression infrastructure while learning how AMD-specific execution, memory, and toolchain constraints shape inference.
  • TPU Performance: Help make vLLM fast and correct on Google TPUs. Build backend, runtime, and compiler integrations with JAX, XLA, Pallas, MLIR, and related tooling; inspect compiler artifacts; work on lowering, fusion, and code generation; and benchmark production-relevant serving across correctness, latency, and throughput.
  • Cloud Orchestration: Build the operational platform that makes large-scale inference deployable and reliable. Work on Kubernetes and custom operators, topology-aware GPU scheduling, zero-downtime vLLM rollouts, token-aware routing, observability, infrastructure-as-code, automated recovery, and bring-your-own-cloud or multi-cloud fleet management.

You are not expected to arrive with experience in every track. We care most about unusual depth or learning velocity in one area, strong fundamentals, and evidence that you can turn a difficult problem into working, measurable software.

Skills and Qualifications

Minimum qualifications:

  • Currently pursuing a bachelor's, master's, or PhD degree in computer science, engineering, mathematics, or a related technical field, and 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: you define what success means, measure results, validate correctness, communicate clearly, and keep iterating until the system works.

Preferred qualifications:

  • 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, Kubernetes, or cloud infrastructure.
  • 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.

Bonus points if you have:

  • 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 rather than staying inside a single abstraction.
  • Created a technical artifact such as a paper, design document, blog post, demo, or talk that clearly explains what you built and what you learned.

Meet Inferact at Waterloo

Interested in learning more about Inferact, vLLM, and the engineering problems you could work on during your co-op? Join us for our University of Waterloo Employer Information Session to meet the team, learn more about Inferact, and hear about the Inference Engineering Co-op opportunity.

  • Venue: Tatham Centre, Room 2218
  • Date: Monday, October 5, 2026
  • Time: 5:00 PM – 7:00 PM ET

Logistics

  • Location: San Francisco, California. This co-op is in-office only at Inferact's San Francisco office and is intended for the University of Waterloo co-op program.
  • Work term: Co-op / internship. Exact dates will align with the applicable Waterloo work term.
  • Compensation: Competitive compensation based on the applicable co-op market and candidate background, plus a housing stipend for the duration of the co-op term.

Inferact, Inc. is an E-Verify company, and you may review the Notice of E-Verify Participation https://drive.google.com/file/d/1TWSDK2aZycxydMvPle230QSwuQtuNIyM/view?usp=sharing and the Right to Work posters in English and Spanish https://drive.google.com/file/d/1WxUM6hcXhb3CuJ_nWgnMmHF99XsuT9sI/view?usp=sharing.

Source: Inferact careers (Ashby)

Similar roles

More roles at Inferact