Note: The job is a remote job and is open to candidates in USA. EnCharge AI is a leader in advanced AI hardware and software systems for edge-to-cloud computing. They are seeking an experienced AI Research Engineer to optimize deep learning models for deployment on edge AI platforms, focusing on model compression, quantization strategies, and efficient inference techniques.
Responsibilities
- Research and develop quantization-aware training (QAT) and post-training quantization (PTQ) techniques for deep learning models
- Implement low-bit precision optimizations (e.g., INT8, BF16)
- Design and optimize efficient inference algorithms for AI workloads, focusing on latency, memory footprint, and power efficiency
- Work with frameworks such as PyTorch, ONNX Runtime, and TVM to deploy optimized models
- Analyze accuracy trade-offs and develop calibration techniques to mitigate precision loss in quantized models
- Collaborate with hardware engineers to optimize model execution for edge devices, and NPUs
- Contribute to research on knowledge distillation, sparsity, pruning, and model compression techniques
- Benchmark performance across different hardware and software stacks
- Stay updated with the latest advancements in AI efficiency, model compression, and hardware acceleration
Skills
- Master's or Ph.D. in Computer Science, Electrical Engineering, or a related field
- Strong expertise in deep learning, model optimization, and numerical precision analysis
- Hands-on experience with model quantization techniques (QAT, PTQ, mixed precision)
- Proficiency in Python, C++, CUDA, or OpenCL for performance optimization
- Experience with AI frameworks: PyTorch, TensorFlow, ONNX Runtime, TVM, TensorRT, or OpenVINO
- Understanding of low-level hardware acceleration (e.g., SIMD, AVX, Tensor Cores, VNNI)
- Familiarity with compiler optimizations for ML workloads (e.g., XLA, MLIR, LLVM)
Company Overview
Company H1B Sponsorship