about 14 hours ago
Santa Clara, CA, USASenior / Staff+
H1B Sponsor
Base Salary
$183k - $261k/yr
Responsibilities
- Build and optimize the model inference path including quantization and KV-cache optimization.
- Fine-tune and evaluate models for bounded tasks and develop evaluation harnesses.
- Design and grow the task execution runtime for dynamic task generation.
- Drive hardware acceleration and support for larger models.
- Collaborate with systems and backend engineers to deliver end-to-end capabilities.
Requirements
- 10+ years of overall industry experience with 4+ years in ML/AI.
- Hands-on experience with fine-tuning, quantization, and inference runtimes.
- Strong proficiency in Python and familiarity with C++ for low-level interop.
- Solid understanding of transformer internals and inference performance levers.
- Fluency with agentic coding systems and a genuine curiosity about agent harnesses.
- Excellent communication skills to convey technical concepts to cross-functional teams.