AI/ML Engineer – Model Optimization & Acceleration

AI/ML Engineer – Model Optimization & Acceleration (8–10 Years)

Location: Bengaluru, India

Experience: 8–10 Years ( If you have experience more than 8 years only apply then)

Open Positions: 3

We are looking for an experienced AI/ML Engineer to optimize and deploy machine learning models across heterogeneous platforms (CPU, GPU, and NPU). If you're passionate about building high-performance, production-ready AI systems and working on cutting-edge technologies, we'd love to hear from you!

Key Responsibilities

Optimize AI models including LLMs, Diffusion Models, CNNs, Computer Vision, Multi-modal, and Speech Models.

Port models across frameworks (PyTorch → ONNX → Runtime).

Deploy and optimize models on GPU/NPU hardware accelerators.

Improve inference latency, throughput, and memory efficiency.

Implement quantization, model compression, and performance tuning.

Profile, benchmark, and debug AI system performance.

Required Skills

Strong expertise in PyTorch and ONNX

Proficiency in Python and C++

Experience with CUDA, ROCm, or GPU acceleration

Strong understanding of Transformers, CNNs, Deep Learning

Hands-on experience in Model Optimization, Quantization, Inference Optimization, and Performance Tuning

Good to Have

Edge AI / Embedded AI deployment

Generative AI or Multi-modal AI

Distributed inference or streaming pipelines

TensorRT, OpenVINO (preferred)

Pay: ₹2,500,000.00 - ₹3,000,000.00 per year

Experience:

AI/ML Engineer – Model Optimization & Acceleration: 8 years (Preferred)

Work Location: In person