09 Sep
|
Glasswing
|
Sydney
Job Description
Glasswing in Sydney, NSW, Australia, is seeking an AI Researcher to push neural network and LLM optimization, with a focus on KV cache efficiency and production-ready innovations. You will evaluate techniques such as pruning, quantization, memory and runtime tuning, then collaborate with engineering to ship changes that materially boost inference speed and model cost.
n
The role emphasizes high-performance code, extensive benchmarking, and mentoring researchers and engineers to scale research into
📌 Senior Ai Researcher: Kv Cache & Inference Optimization (Sydney)
🏢 Glasswing
📍 Sydney