Description

You will own the performance engineering and optimization of Generative AI and LLM software applications.

This role is on-site.

Responsibilities

• Improve and analyze performance of Generative AI and LLM applications.
• Enable and optimize OSS/ISV applications for Fujitsu's new processor.
• Develop new algorithms for ML/DL frameworks and tune technologies using AI framework engineering.
• Enhance performance of Generative AI and LLM models for inferencing and fine-tuning.
• Troubleshoot, debug, and fix bugs while upgrading software and applications.

Required Skills

• 5+ years of professional software development experience.
• Strong programming expertise in Python and C++.
• Hands-on experience in High Performance Computing (HPC) environments.
• In-depth knowledge of Generative AI and LLM Ops, including fine-tuning and inference optimization.
• Experience with AI/ML frameworks such as TensorFlow, PyTorch, or ONNX.
• Familiarity with model optimization techniques like operator fusion, quantization, and sparsity.
• Ability to design and develop algorithms for ML/DL frameworks.
• Experience in OSS/ISV application optimization and performance benchmarking.

Preferred Skills

• Master's/M.Tech or PhD in Computer Science or a related field.
• Exposure to agile methodologies and managing multiple concurrent projects efficiently.

Key Skills

Education

Any Graduate