AI model optimization & acceleration Engineer

L&T Technology Services; Bengaluru; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

L&T Technology Services in Bengaluru seeks an AI Engineer to optimize and deploy ML models across CPU, GPU, and NPU, delivering scalable AI systems for robotics, healthcare, and automotive.

The role emphasizes production readiness, latency optimization, and hardware acceleration, with 4-10 years of experience in Python/C++, and a strong foundation in transformers and CNNs.

Qualifications

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

Responsibilities

• Optimize diverse models: generative (LLMs, diffusion), vision (classification, detection, segmentation), multi-modal, and speech.
• Deploy on hardware accelerators (GPU/NPU) and optimize performance.
• Improve inference latency, throughput, and memory (batching, caching, parallelism, fusion).
• Apply quantization and model compression (FP32 to lower precision).
• Profile and debug system and model performance.

Skills

Python

C++

Transformers

CNNs

Inference optimization

Tools

CUDA

ROCm

Job description

Seeking an AI Engineer to optimize and deploy ML models across heterogeneous platforms (CPU, GPU, NPU).

Work on scalable, production-ready AI systems across domains like robotics, healthcare, and automotive.

Experience : 4-10 Years

Job Responsibilities / Day-to-Day Activities

Qualifications & Experiences:

Key Responsibilities

• Optimize diverse models: generative (LLMs, diffusion), vision (classification, detection, segmentation), multi-modal, and speech
• Deploy on hardware accelerators (GPU/NPU) and optimize performance
• Improve inference latency, throughput, and memory (batching, caching, parallelism, fusion)
• Apply quantization and model compression (FP32 to lower precision)
• Profile and debug system and model performance

Required Skills

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

Good to Have

• Edge AI or embedded deployment
• Distributed inference or streaming pipelines