Staff AI Engineer

Zoom Video Communications
Seattle
Workplace: HybridFull timeUSD 151,800 - 332,200 annuallyFunction: Data Science & Machine LearningExperience: 5+ yearsSkills: ["Systems thinking","Technical design","Profiling","Incident response","Collaboration"]

Design and own Zoom’s high-scale inference systems that power real-time communication, vision, and language AI models. Build and optimize serving for large transformer and multimodal workloads, including 100B+ and MoE architectures, using techniques like speculative decoding, continuous batching, KV-cache management, and quantization. Work hands-on with inference frameworks and CUDA kernels, deliver end-to-end deployment with latency SLO monitoring, and partner with research to implement model changes efficiently.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Zoom Video Communications
Zoom Video Communications
5 days ago

Staff AI Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 17 hours agoStatus: Live
Reposted: similar role first listed 1 month ago

Job Summary

Design and own Zoom’s high-scale inference systems that power real-time communication, vision, and language AI models. Build and optimize serving for large transformer and multimodal workloads, including 100B+ and MoE architectures, using techniques like speculative decoding, continuous batching, KV-cache management, and quantization. Work hands-on with inference frameworks and CUDA kernels, deliver end-to-end deployment with latency SLO monitoring, and partner with research to implement model changes efficiently.
Location: Seattle
Workplace: Hybrid
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Mid level

Key Responsibilities

  • •Design, implement, and own inference serving systems for large-scale transformer and multimodal models at production scale.
  • •Implement and tune inference optimizations such as speculative decoding, continuous batching, KV cache management, prefill/decode disaggregation, and quantization (INT4/INT8/FP8).
  • •Contribute to and customize inference frameworks (vLLM, TensorRT-LLM, SGLang, or equivalent) for Zoom’s production requirements.
  • •Write and profile CUDA kernels and custom ops when framework-level optimization is insufficient.
  • •Own end-to-end deployment from model packaging and serving API design through latency SLO monitoring and incident response.

Pay and Benefits

Salary: USD 151,800 - 332,200 annually

Key Requirements

  • •Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, or related field, or equivalent practical experience.
  • •5+ years of software engineering experience with significant time on inference systems or ML infrastructure at production depth.
  • •Hands-on experience with an inference framework for serving (vLLM, TensorRT-LLM, SGLang, or ONNX Runtime).
  • •GPU programming experience, including CUDA kernel development, memory optimization, and profiling with Nsight or equivalent tools.
  • •Production experience serving LLMs or large vision models, including owning latency SLOs and shipping optimizations that improve throughput and latency.
Experience:5+ yearsAI infrastructureML infrastructureLLMsLarge vision modelsTransformer modelsMultimodal modelsMoEQuantizationInference serving
Education:
Skills:Systems thinkingTechnical designProfilingIncident responseCollaboration
Tech Stack:PythonC++CUDANsightVLLMTensorRT-LLMSGLangONNX RuntimeTensorRTCUDA kernelsCUDA kernel developmentXLATritonINT4INT8FP8MoEKV cacheSpeculative decodingContinuous batching

Company Brief

Zoom Video Communications
Provides video conferencing, chat, phone, webinar, and collaboration software for businesses, schools, and individuals. Its platform is widely used for remote meetings, virtual events, and hybrid work communication.
Industry: SaaS
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Public Company
Valuation: Public Company (Market Cap in USD)
Funding: IPO / Publicly Listed
Headquarters: San Jose, United States
Founded: 2011
WebsiteLinkedIn