AI Research Engineer

Job Summary

Driving innovation in model serving and inference architectures, the full-time AI Research Engineer will optimize model deployment strategies for advanced AI systems in a 100% remote environment.

Key responsibilities

• Design and deploy model serving architectures that optimize throughput, latency, and memory usage across diverse environments
• Build and monitor inference tests in production environments, tracking performance metrics and documenting results against benchmarks
• Analyze computational efficiency to identify and resolve bottlenecks in the serving pipeline, ensuring scalability and reliability on resource-constrained systems

Required qualifications

• PhD in Computer Science, NLP, Machine Learning, or a related field with a strong track record in AI R&D
• Proven experience in low-level kernel optimizations and inference optimization on mobile devices
• Deep understanding of model serving architectures and inference optimization techniques
• Strong expertise in writing GPU kernels for mobile devices and developing end-to-end inference pipelines
• Knowledge of advanced techniques such as Tensor Parallelism and Diffusion Models