Senior Agentic Retrieval Systems Engineer – LLM Pipelines

NVIDIA; Santa Clara (CA); On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a System Software Engineer - Agentic Retrieval to build and optimize GPU-accelerated data pipelines for multimodal content. You will collaborate with LLM researchers to create scalable, production-ready tools and libraries, focusing on performance, cost, and accuracy in Generative AI workflows.

The role emphasizes cloud familiarity, MLOps, and cross-functional collaboration across teams to advance the Agentic Retrieval ecosystem and drive efficient training data processing.

Qualifications

• Bachelor’s or Master’s Degree in Computer Science, Computer Engineering, or related field.
• 6+ years of experience in a similar or related role.
• Experience delivering software in a cloud context and familiar with cloud infrastructure patterns.
• Knowledge of MLOps technologies such as Docker-Compose, Containers, Kubernetes.
• Excellent NLP/LLM/VLM, Generative AI, and Agentic Retrieval workflow understanding.
• Self-starter with growth mindset and willingness to share findings.
• Outstanding communication skills for distilling complex topics.
• Ability to work with multi-functional teams across geographies.

Responsibilities

• Develop and optimize Rust-based data processing frameworks for large datasets on GPU-accelerated environments.
• Lead development and optimization of Agentic Retrieval pipelines targeting GPU acceleration and best model performance.
• Build and optimize full-stack GPU-accelerated data prep pipelines for multimodal models; benchmark and optimize algorithms.
• Collaborate with LLM/ML researchers to develop production-ready tools and library features.
• Create products to enhance employee productivity using Gen-AI and co-pilot experiences.
• Integrate systems to enable a unified user experience across applications.
• Maintain a robust CD pipeline to move changes to production safely and quickly.
• Provide peer review and promote adoption of new frameworks and technologies.

Skills

NLP/LLM expertise

Cloud software development

Cross-functional collaboration

Strong communication

Education

Bachelor’s or Master’s Degree in CS/CE

Tools

Docker-Compose

Containers

Kubernetes

Job description

NVIDIA is seeking a System Software Engineer - Agentic Retrieval to build and optimize GPU-accelerated data pipelines for multimodal content. You will collaborate with LLM researchers to create scalable, production-ready tools and libraries, focusing on performance, cost, and accuracy in Generative AI workflows.

The role emphasizes cloud familiarity, MLOps, and cross-functional collaboration across teams to advance the Agentic Retrieval ecosystem and drive efficient training data processing.