Job DescriptionProject Details
nAI model optimization & acceleration
n

nJob Description
nSeeking an AI Engineer to optimize and deploy ML models across heterogeneous platforms (CPU, GPU, NPU).
nWork on scalable, production-ready AI systems across domains like robotics, healthcare, and automotive.
n

nExperience : 4-10 Years
n

nJob Responsibilities / Day-to-Day Activities
n

nQualifications & Experiences:
nKey Responsibilities
n• Optimize diverse models: generative (LLMs, diffusion), vision (classification, detection, segmentation), multi-modal, and speech
n• Port models across frameworks (e.g., PyTorch → ONNX → runtimes)
n• Deploy on hardware accelerators (GPU/NPU) and optimize performance
n• Improve inference latency, throughput, and memory (batching, caching, parallelism, fusion)




n• Apply quantization and model compression (FP32 → lower precision)
n• Profile and debug system and model performance
n

nRequired Skills
n• Robust in PyTorch (or similar), ONNX (or equivalent)
n• Proficient in Python and C++
n• Experience with GPU/hardware acceleration (CUDA/ROCm or similar)
n• Solid understanding of deep learning models (transformers, CNNs)
n• Knowledge of optimization, quantization, and performance tuning
n

nGood to Have
n• Edge AI or embedded deployment
n• Generative or multi-modal AI systems
n• Distributed inference or streaming pipelines

📌 AI model optimization (Karnataka)
🏢 L&T Technology Services
📍 Karnataka