Senior Staff / Principal Machine Learning Scientist, AI Inference & Optimization

📋 Description

• Own the model inference path: quantization, KV-cache, batching.
• Tune latency and memory on constrained hardware.
• Build runtime for bounded AI tasks with production signals.
• Collaborate with systems and backend engineers to ship end-to-end.
• Push toward dynamic task generation and context compaction.

🎯 Requirements

• 10+ years in tech; 4+ years ML/AI hands-on.
• Fine-tune with LoRA/QLoRA; quantization (GGUF/AWQ/GPTQ).
• Runtimes: vLLM, TensorRT-LLM, ONNX Runtime, llama.cpp.
• Strong Python; C++ interop as needed.
• Transformer internals: KV-cache, attention, batching, memory.
• Agentic coding systems (Claude Code, Pi, Codex) experience.
• Education: MS in CS/ML/EE; PhD preferred.

🎁 Benefits

• High-impact ownership of a net-new product.
• Cutting-edge inference tech: quantization, KV-cache, memory management.
• Real production scale with live customer signals.
• Comprehensive benefits, including health plan.