AI Software Engineer
Not Disclosed•Full-TimeHybrid
location_on301, Union Street, Central Business District, Belltown, Seattle, King County, Washington, 98101, United States
The Team
You will join a dynamic AI Infrastructure team focused on enabling high-performance AI across Zoom's products and services. The team builds the core systems that support model training, deployment, and inference at scale, driving innovation in areas such as real-time communication, computer vision, and natural language understanding.
About the Role
You'll design, implement, and own the inference systems that serve Zoom's AI models at production scale, across real-time communication, vision, and language workloads. You'll be hands-on with kernel-level optimisation, inference framework internals, and production serving infrastructure, working closely with research and platform teams to push the boundary on latency, throughput, and cost.
About Us
Zoomies help people stay connected so they can get more done together. We set out to build the best collaboration platform for the enterprise, and today help people communicate better with products like Zoom Contact Center, Zoom Phone, Zoom Events, Zoom Apps, Zoom Rooms, and Zoom Webinars. We're problem-solvers, working at a fast pace to design solutions with our customers and users in mind. Find room to grow with opportunities to stretch your skills and advance your career in a collaborative, growth-focused environment.
Ways of Working
Our structured hybrid approach is centered around our offices and remote work environments. The work style of each role, Hybrid, Remote, or In-Person is indicated in the job description/posting.
Our Commitment
At Zoom, we believe great work happens when people feel supported and empowered. We're committed to fair hiring practices that ensure every candidate is evaluated based on skills, experience, and potential. If you require an accommodation during the hiring process, let us know—we're here to support you at every step.
We welcome people of different backgrounds, experiences, abilities and perspectives including qualified applicants with arrest and conviction records and any qualified applicants requiring reasonable accommodations in accordance with the law.
Think of this opportunity as a marathon, not a sprint! We're building a strong team at Zoom, and we're looking for talented individuals to join us for the long haul. No need to rush your application – take your time to ensure it's a good fit for your career goals. We continuously review applications, so submit yours whenever you're ready to take the next step.
Our interviews are supported by BrightHire, a tool that helps us create a consistent and thoughtful interview experience and may include recordings. Please refer to our candidate privacy statement for more information of how we use your data.
Work location
Work model: Hybrid
301, Union Street, Central Business District, Belltown, Seattle, King County, Washington, 98101, United States
Seattle, Washington
Key Responsibilities
- check_circleDesign and build high-performance inference serving systems for large-scale transformer and multimodal models
- check_circleOwn end-to-end model deployment from packaging and API design to latency SLO monitoring and incident response
- check_circlePartner with research teams to translate model architecture changes into inference-efficient implementations
- check_circleDrive technical design and set standards for inference engineering practices across the team
- check_circleContribute to and customize inference frameworks such as vLLM, TensorRT-LLM, and SGLang for production requirements
- check_circleWrite and profile CUDA kernels and custom operations where framework-level optimization is insufficient
- check_circleImplement and tune inference optimizations including speculative decoding, continuous batching, and quantization
Requirements
- verified5+ years of software engineering experience
- verifiedHands-on experience with vLLM, TensorRT-LLM, SGLang, or ONNX Runtime
- verifiedGPU programming experience with CUDA kernel development
- verifiedProduction experience serving LLMs or large vision models
- verifiedProficiency in Python and C++
- verifiedDepth in speculative decoding, continuous batching, KV cache design, quantisation pipelines, or prefill/decode disaggregation
Nice to Have
Experience with MoE models or 100B+ parameter deployments. Familiarity with disaggregated serving architectures or multi-node inference. Background in compiler-level optimisation (XLA, Triton, or similar).
Similar Job Opportunities
Frequently asked questions about AI Software Engineer at Zoom
What does a AI Software Engineer at Zoom do?expand_more
Day-to-day, the AI Software Engineer at Zoom will design and build high-performance inference serving systems for large-scale transformer and multimodal models; own end-to-end model deployment from packaging and api design to latency slo monitoring and incident response; partner with research teams to translate model architecture changes into inference-efficient implementations; and drive technical design and set standards for inference engineering practices across the team.
What are the requirements for this AI Software Engineer role?expand_more
To qualify for the AI Software Engineer at Zoom position, applicants should have: 5+ years of software engineering experience; Hands-on experience with vLLM, TensorRT-LLM, SGLang, or ONNX Runtime; GPU programming experience with CUDA kernel development; Production experience serving LLMs or large vision models; Proficiency in Python and C++; and Depth in speculative decoding, continuous batching, KV cache design, quantisation pipelines, or prefill/decode disaggregation.
Where is the AI Software Engineer role at Zoom located?expand_more
AI Software Engineer at Zoom is based in 301, Union Street, Central Business District, Belltown, Seattle, King County, Washington, 98101, United States. This is a hybrid role.
Is this AI Software Engineer job remote, hybrid, or on-site?expand_more
Zoom has listed this AI Software Engineer role as hybrid.
How much experience is required for this AI Software Engineer role?expand_more
AI Software Engineer at Zoom typically requires 5+ years of relevant experience at the senior level.
What skills do you need for the AI Software Engineer role at Zoom?expand_more
Key skills for AI Software Engineer at Zoom include Ai Infrastructure; Model Training; Model Deployment; Inference; Real-Time Communication; Computer Vision; Natural Language Understanding; and Kernel-Level Optimisation.
What category does the AI Software Engineer role belong to?expand_more
AI Software Engineer at Zoom is part of the it job category on Recrutus.