All jobs
Senior ML Engineer | Kimchi (Inference Stack Optimization)
Cast AI
Netherlands · Remote possibleSenior (5–10 years)Full-timePosted 15 days ago
About the job
What you'll do
You will own the optimization of the inference stack to improve throughput, latency, and cost-efficiency. This involves tuning loaders, schedulers, and kernels while managing distributed inference topologies and quantization strategies.
What they're looking for
You must have 5+ years of experience building real ML systems with deep expertise in inference infrastructure. Proficiency in Python and hands-on experience with engines like vLLM or SGLang are required.
Full description