Description

You will design and build AI solution architectures, focusing on SDK modules and LLM deployment pipelines.

This role is on-site.

Responsibilities

• Design and implement SDK modules, including preprocessing, postprocessing, model orchestration, and inference engines.
• Develop APIs and utilities for rapid prototyping and production deployment of Deep Learning and LLM workloads.
• Benchmark and optimize SDK performance against target hardware, enabling OSS/ISV applications for new processor lines.
• Troubleshoot, debug, and resolve issues while upgrading software and applications.

Required Skills

• 5+ years of professional software development experience.
• Strong proficiency in C++ and Python.
• In-depth knowledge of AI/ML frameworks: TensorFlow, PyTorch, and ONNX.
• Hands-on experience with LLM Ops, model orchestration, and deployment pipelines.
• Solid understanding of Deep Learning architectures and LLMs, including inference optimization.
• Experience in hardware-software co-optimization and performance benchmarking.
• Familiarity with Linux, CMake/Bazel, Docker, and Kubernetes.
• Expertise in software architecture, design patterns, and system scalability.
• Experience working in Agile environments and managing concurrent projects.

Key Skills

Education

Any Graduate