TL, Research Inference

📋 Description

• Design and build high-performance inference runtimes for large-scale AI models.
• Own and optimize core execution paths: model execution, memory, batching, scheduling.
• Develop and improve distributed inference across multiple GPUs and runtime coordination.
• Implement and optimize inference-critical operators and kernels.
• Partner with research teams to ensure new model architectures are supported in inference.
• Diagnose and resolve performance bottlenecks via profiling and debugging.
• Contribute to observability, correctness, and reliability of large-scale AI systems.

🎯 Requirements

• Have experience building production inference systems, not just training or running models.
• Experience with GPU-centric performance engineering, including memory behavior and latency/throughput tradeoffs.
• Have worked on multi-GPU or distributed systems with batching, scheduling, or runtime coordination.
• Can reason end-to-end about inference pipelines, from request handling to execution and output streaming.
• Able to implement research ideas within real system and performance constraints.
• Enjoy solving hard, ambiguous systems problems that emerge at scale.
• Prefer hands-on technical ownership and execution over abstract design work.