Staff Software Engineer

Summary

Join ServiceNow, a global leader in AI-enhanced technology, and contribute to our mission of making the world work better. As a key member of our team, you will develop and maintain APIs using NVIDIA Triton Inference Server for scalable deployment of Large Language Models (LLMs). You will also implement and optimize pre-processing and post-processing pipelines, work with Retrieval-Augmented Generation (RAG) frameworks, and collaborate with cross-functional teams. This role requires proven experience with NVIDIA Triton and a strong understanding of LLM techniques. We offer a competitive salary and benefits package, including health plans, 401(k) matching, and flexible time away.

Requirements

• Proven experience with NVIDIA Triton Inference Server and its APIs
• Strong understanding of pre-processing and post-processing techniques for LLMs
• Familiarity with Retrieval-Augmented Generation (RAG) and other LLM mechanisms
• Proficient in Python and relevant ML frameworks (e.g., PyTorch, TensorFlow)
• Strong problem-solving skills and ability to work in a fast-paced environment

Responsibilities

• Develop and maintain APIs using NVIDIA Triton Inference Server for scalable deployment of Large Language Models (LLM)
• Implement and optimize pre-processing and post-processing pipelines tailored for LLMs to improve accuracy and efficiency
• Work with Retrieval-Augmented Generation (RAG) frameworks to enhance the model’s response generation capabilities
• Collaborate with data scientists, software engineers, and product teams to integrate and deploy ML solutions into production
• Troubleshoot and resolve issues related to model inference, performance, and scalability

Benefits

• Health plans, including flexible spending accounts
• A 401(k) Plan with company match
• ESPP
• Matching donations
• A flexible time away plan
• Family leave programs (subject to eligibility requirements)
• For positions in California (outside of the Bay Area), we offer a base pay of $142,700 - $249,800, plus equity (when applicable), variable/incentive compensation and benefits