Principal Research Engineer

Principal Research Engineer, Applied AI at EnCharge AI

About the Role & Company:

EnCharge AI is building the next generation of in-memory computing platforms. Our architecture delivers a revolutionary 10x improvement in compute energy efficiency for AI inference workloads. We are seeking an experienced Research Engineer to push the boundaries of model capability, quality, and efficiency at our hardware-software intersection.

Key Responsibilities:

• Algorithmic Acceleration: Implement state-of-the-art techniques (quantization, sparsity, speculative decoding) to optimize inference latency and throughput while managing power consumption.
• Hardware Co-Design: Partner with hardware and compiler teams to align algorithmic improvements with our silicon architecture's strengths.
• Evaluation & Profiling: Build robust benchmarking frameworks to characterize tradeoffs between model quality, latency, and efficiency metrics.
• Applied Research: Develop fine-tuning workflows for modern AI models (LLMs, diffusion generators) using techniques like LoRA and adapters. Stay current with the evolving landscape of ML architectures.