AI Engineer

Zoom • Seattle, WA

11d • $137,700 - $275,400

About The Position

Join Zoom's AI Infrastructure team, which builds core systems for model training, deployment, and inference across Zoom products and services. The team works on high-performance AI applications in areas including real-time communication, computer vision, and natural language understanding.

In this role, you will build and optimize production inference systems for Zoom's AI models. Working with senior inference engineers, research teams, and platform teams, you will profile serving workloads, identify latency, throughput, and cost bottlenecks, and implement improvements. The work involves inference frameworks, GPU profiling, and serving infrastructure, as well as production support for the services you build.

The position offers a salary range of $137,700 to $275,400. Starting pay depends on qualifications and experience, and compensation may vary based on location. Zoom describes its work approach as structured hybrid, with the work style for each role indicated in the posting; this posting does not specify a work style for this role.

Requirements

• A degree in Computer Science, Computer Engineering, or a related field, or equivalent practical experience; an MS or PhD is preferred.
• 0–3 years of software engineering experience; internships, research, and open-source work in ML systems count.
• Hands-on experience serving and modifying at least one inference framework, such as vLLM, SGLang, TensorRT-LLM, or ONNX Runtime; exporting models alone is not sufficient.
• Working knowledge of LLM inference on GPUs, including memory bandwidth, KV cache, batching, and communication across GPUs.
• Experience profiling and debugging GPU performance, with evidence of an optimization that was measured and shipped.
• Depth in at least one of speculative decoding, continuous batching, KV cache design, quantization, or distributed or multi-GPU serving.
• Strong programming skills in Python and C++, and comfort reading and modifying large framework codebases.

Nice To Haves

• Merged contributions to vLLM, SGLang, TensorRT-LLM, PyTorch, or similar projects.
• CUDA, Triton, or CUTLASS kernel development experience.
• Experience serving MoE or 100B+ parameter models, or multi-node inference using NCCL or RDMA/RoCE.
• Graduate coursework or research in ML systems, compilers, or high-performance computing.

Responsibilities

• Build, tune, and maintain components of Zoom's inference serving stack for transformer and multimodal models, including large and Mixture-of-Experts (MoE) architectures.
• Implement and evaluate inference optimizations, including speculative decoding, continuous batching, KV cache management, parallelism layouts, and INT4, INT8, or FP8 quantization.
• Extend and customize inference frameworks such as vLLM, SGLang, TensorRT-LLM, or equivalent to support new models and Zoom's production requirements.
• Profile GPU workloads using Nsight Systems or equivalent tools, investigate performance regressions, and validate improvements with reproducible benchmarks.
• Build and improve internal tools for benchmarking, performance modeling, and serving configuration.
• Partner with researchers to bring new model architectures into production efficiently.
• Contribute to on-call and production support for the services you build, with guidance from senior engineers.

Benefits

• Zoom offers a benefits program with perks, benefits, and options intended to support employees' physical, mental, emotional, and financial health, work-life balance, and community involvement.
• The posting mentions base salary, bonus, and equity value as elements of Zoom's Total Direct Compensation philosophy.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level