Deep Learning Software Engineer, TensorRT Performance
Location
California
Posted
64 days ago
Salary
$124K - $195.5K / year
Seniority
Mid Level
Job Description
Deep Learning Software Engineer, TensorRT Performance
NVIDIA
• Establish groundbreaking performance benchmarking methodologies and analysis workflows and identify performance issues and opportunities for NVIDIA’s inference ecosystem (e.g. TensorRT/TensorRT-EdgeLLM/Torch-TensorRT) • Contribute features and code to NVIDIA/OSS inference frameworks including but not limited to TensorRT/TensorRT-EdgeLLM/Torch-TensorRT. • Develop new model pipelines for NVIDIA’s inference ecosystem with optimized performance including but not limited to areas like quantization, scheduling, memory management, and distributed inference to set the gold standard for Gen AI performance. • Work with cross-collaborative teams inside and outside of NVIDIA across generative AI, automotive, robotics, image understanding, and speech understanding to set directions and develop innovative inference solutions. • Scale performance of deep learning models across different architectures and types of NVIDIA accelerators.
Job Requirements
- Bachelors, Masters, PhD, or equivalent experience in relevant fields (Computer Science, Computer Engineering, EECS, AI).
- 2 years of relevant software development experience.
- Strong C++, Python programming and software engineering skills
- Experience with DL frameworks (e.g. PyTorch, JAX, TensorFlow, ONNX) and inference libraries (e.g. TensorRT, TensorRT-LLM, vLLM, SGLang, FlashInfer).
- Experience with performance analysis and performance optimization
Benefits
- equity
- benefits
Related Guides
Related Job Pages
More Full-stack Engineer Jobs
Senior Software Developer, Systems Software
DMI (Digital Management, LLC)At the Intersection of Public and Private Sectors
• Designs, develops, and delivers enterprise-grade software solutions supporting TSA’s mission-critical applications • Works within Agile and DevSecOps delivery frameworks to develop secure, scalable, and maintainable code • Collaborates closely with systems engineers, cloud architects, and the O&M contractor • Ensures software deliverables are transition-ready and fully documented for sustainment • Conduct requirements analysis, software design, coding, unit and integration testing, code review • Develops technical documentation including API specifications, developer guides, and runbooks • Supports software migrations and modernization efforts • Participates in operational testing periods post-transition • Available for post-deployment troubleshooting
• Directs day-to-day work prioritization • Plans, organizes, coordinates applications development • Leads projects regarding application analysis, coding, testing and enhancement • Provides guidance and mentorship to all engineers
• Develop and maintain responsive, user-friendly web applications using HTML, CSS, JavaScript, React, Next.js, and TypeScript. • Implement state management with Redux and style components using CSS frameworks like Bootstrap and Tailwind. • Build scalable microservices with Node.js, ensuring high availability and performance. • Develop and integrate RESTful and GraphQL APIs for efficient and secure communication between services. • Write and maintain unit tests for both backend services and frontend applications to ensure code quality. • Utilize AWS services like Lambda to build, deploy, and manage server less microservices, optimizing for performance and cost. • Implement search capabilities with OpenSearch, including setting up indexes, managing queries, and optimizing performance. • Create and execute queries with DynamoDB and relational DB. • Ensure software meets performance and security requirements. • Analyze logs, debug applications, and implement both immediate and long-term improvements. • Review team members' code for adherence to coding standards, structure, and best practices. • Assist in troubleshooting and resolving technical issues during development. • Provide technical expertise, guidance, and mentorship to team members, helping them solve complex problems. • Create and maintain comprehensive technical documentation. • Collaborate closely with cross-functional teams, including DevOps, QA, and product management.
Staff Software Engineer
EverbridgeAfter 9/11, Everbridge was founded to improve the way people communicate and find one another in critical situations. Through its Software-as-a-Service-based communications platfor
• Designing, developing, and supporting software solutions for the company’s critical event management platform and various web and mobile applications built on top of the core platform. • Collaborating directly with product management, QA, technical operations, and cross functional team leads to ensure the timely completion of projects. • Creating and maintaining robust, high-volume, and scalable applications to meet performance and reliability standards. • Designing and implementing microservices architectures that support modular, maintainable, and extensible systems. • Defining and implementing automated tests to maintain software quality and accelerate development cycles. • Building applications and infrastructure that run in AWS, following best practices for cloud-native development. • Participating in code reviews to ensure code quality, maintainability, and alignment with team standards. • Contributing as a scrum team member and technical leader, ensuring timely project delivery with high-quality output. • Designing, implementing, and optimizing data pipelines and analytics solutions using tools like Snowflake and Looker to support data-driven decision-making. • Monitoring and managing cloud infrastructure costs proactively, driving efficiency and implementing strategies for cost optimization. • Developing and maintaining scalable, event-driven architectures using Kafka or similar queue-based messaging systems to ensure reliable and efficient data processing.




