Research Engineer – Inference
Core
Optimize and deploy state-of-the-art AI models for efficient, real-world inference on local hardware.
Role type
Senior IC research engineer (inference optimization)
Builds
High-performance systems for low-latency, high-throughput model serving
Domain
AI inference, systems engineering, hardware optimization
Deliverable
production ML models
Required skills
Machine learning engineering, systems engineering, deep learning frameworks, model inference optimization, high-performance concurrent code, computer science fundamentals
Preferred skills
Model optimization techniques (quantization, pruning, distillation, compilation), inference runtimes, hardware proximity, edge/on-device AI deployment, distributed systems
Technologies
Python, PyTorch, Rust, CUDA, PostgreSQL, Linux
Responsibilities
Design and implement high-performance systems for model serving, work across the stack from model architecture to runtime systems and APIs, build infrastructure for on-device and on-prem environments, collaborate with research and product teams
Seniority
Senior, hands-on IC
