Research Engineer

Focused on deploying and optimizing frontier AI models in production, the full-time remote Research Engineer will manage the systems that transform research breakthroughs into real-time products, ensuring high performance in latency-sensitive applications. Key responsibilities Deploy state-of-the-art models to production and oversee the transition from research to serving infrastructure Optimize inference performance across the stack, utilizing techniques such as quantization and batching strategies Build and tune high-performance serving systems for real-time, streaming workloads Required qualifications Experience deploying and serving ML models in production, particularly for latency-sensitive applications Strong engineering skills in GPU programming and inference optimization (e.g., CUDA, Triton, TensorRT) Ability to autonomously diagnose and eliminate bottlenecks across the serving stack Demonstrated capability in creating tooling for measuring performance characteristics