AI Engineer

Responsibilities

• check_circle Design and build high-performance inference serving systems for large-scale transformer and multimodal models (including 100B+ and MoE architectures)
• check_circle Implement and tune inference optimisations: speculative decoding, continuous batching, KV cache management, prefill/decode disaggregation, and quantisation (INT4/INT8/FP8)
• check_circle Contribute to and customise inference frameworks (vLLM, TensorRT-LLM, SGLang, or equivalent) for Zoom's production requirements
• check_circle Write and profile CUDA kernels and custom ops where framework-level optimisation is insufficient
• check_circle Own end-to-end deployment: from model packaging and serving API design to latency SLO monitoring and incident response
• check_circle Partner with research to translate model architecture changes into inference-efficient implementations
• check_circle Drive technical design and set the bar for inference engineering practices across the team
• check_circle A Bachelor's or Master's degree in Computer Science, Electrical Engineering, or a related technical field, or equivalent practical experience
• check_circle 5+ years of software engineering experience, with significant time spent on inference systems or ML infrastructure at production depth
• check_circle Hands-on experience with at least one major inference framework: vLLM, TensorRT-LLM, SGLang, or ONNX Runtime (serving, not just export)
• check_circle GPU programming experience: CUDA kernel development, memory optimisation, and profiling with Nsight or equivalent tools
• check_circle Production experience serving LLMs or large vision models - you've owned latency SLOs, debugged throughput regressions, and shipped optimisations that moved the needle
• check_circle Depth in at least two of: speculative decoding, continuous batching, KV cache design, quantisation pipelines, prefill/decode disaggregation
• check_circle Strong systems instincts in Python and C++; ability to read and modify framework internals

Preferred qualifications

• Advanced degree (Master's or PhD) in a relevant technical field
• 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)

About the company