Senior Multimodal Retrieval Systems Engineer

NVIDIA; United States; Remote; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA in the United States is seeking a System Software Engineer - Agentic Retrieval to build and optimize GPU-accelerated data pipelines for multi-modal content and LLM workflows.

You will collaborate with LLM researchers, implement benchmarking and profiling in Python, and contribute to production-ready tools across the Gen-AI stack, delivering scalable, efficient pipelines and improved retrieval quality.

Qualifications

• 6+ years of experience in a similar or related role.
• Experience delivering software in a cloud context and is familiar with the patterns and process of managing cloud infrastructure.
• Knowledge of MLOps technologies such as Docker-Compose, Containers, Kubernetes, data center deployments etc
• Excellent in-depth hands-on understanding of NLP, LLM, VLM, Generative AI, and Agentic Retrieval workflows
• Self-starter with a passion for growth, enthusiasm for continuous learning and sharing findings across the team
• Outstanding communication skills for distilling sophisticated topics down to understandable, impactful conclusions.
• Ability to work successfully with multi-functional teams, principals, and architects.

Responsibilities

• Develop and optimize Rust-based data processing frameworks, ensuring efficient handling of large datasets on GPU-accelerated environments, vital for LLM training.
• Lead development and iterative optimization of components for Agentic Retrieval pipelines, ensuring they demonstrate GPU acceleration & the best performing models for improved TCO.
• Collaborate with teams of LLM & ML researchers in the development of full-stack, GPU-accelerated data preparation pipelines for multimodal models Implement benchmarking, profiling, and optimization of innovative algorithms in Python in various system architectures, specifically targeting LLM applications.
• Work closely with diverse teams to understand requirements, build & evaluate POCs, and develop roadmaps for production level tools and library features within the growing LLM ecosystem.
• Build amazing products to improve employee productivity using Gen-AI & Co-pilot experiences!
• Develop integrated systems enabling unified experience across applications and driving insights for end-to-end user experience.
• Help build and maintain our Continuous Delivery pipeline with the goal of moving changes to production faster and safer, while ensuring key operational standards.
• Provide peer reviews to other specialists including feedback on performance, scalability, and correctness and actively contribute to the adoption of frameworks, standards, and new technologies

Skills

NLP

LLM

VLM

Generative AI

Agentic Retrieval

System software engineering

Python

Rust

GPU acceleration

Education

Bachelor’s or Master’s Degree in Computer Science/Engineering

Tools

Docker-Compose

Containers

Kubernetes

CI/CD

Job description

NVIDIA in the United States is seeking a System Software Engineer - Agentic Retrieval to build and optimize GPU-accelerated data pipelines for multi-modal content and LLM workflows.

You will collaborate with LLM researchers, implement benchmarking and profiling in Python, and contribute to production-ready tools across the Gen-AI stack, delivering scalable, efficient pipelines and improved retrieval quality.