SSE - Optimization Engineer

About the role

hardware accelerators, and edge devices. The role focuses on quantization, model compression, high-performance kernel implementation, transformer optimization, and production deployment.

What you'll do

• Develop and optimize deep learning models (CNNs
• LLMs, MoE) for efficient inference across CPU, GPU, hardware accelerators, and
• Design and implement quantization algorithms
• Apply model compression techniques such as
• Pruning, decomposition, and distillation

What you need

• 4–7 years in software engineering
• Data structures
• Python
• C++
• LLMs
• PyTorch
• Deep learning
• B.Tech or B.E. or M.Tech or M.Sc

Good to have

• Machine learning