Research Engineer, AI Models

The Opportunity:

• Modern AI workloads represent compute-intensive frontiers where our hardware's energy efficiency provides advantages.
• We are seeking a Research Engineer to push boundaries in AI model capability, quality, and efficiency.

Key Responsibilities:

• Algorithmic Acceleration: Research and implement techniques like quantization, sparsity, distillation, speculative decoding, and caching.
• Hardware Co-Design: Partner with hardware and compiler teams to ensure algorithmic improvements translate to silicon gains.
• Evaluation: Build profiling tools and benchmarking frameworks to measure model quality and efficiency metrics.

Qualifications:

• 5+ years experience in ML research, applied ML, or ML systems.
• Strong fundamentals in Python and PyTorch.
• Hands-on experience with transformers, diffusion models, and fine-tuning large models.

Nice to Have:

• Experience with efficient inference techniques such as KV cache optimization and MoE routing.
• Background in hardware-aware ML optimization or quantization.