NVIDIA is widely considered one of the world's most desirable employers in technology. We have some of the world's most forward-thinking and passionate people working for us. If you're creative and autonomous, we want to hear from you!
Senior System Software Engineer – Dynamo-Triton Inference Server
Location
California + 1 moreAll locations: California | Washington
Posted
36 days ago
Salary
$152K - $287.5K / year
Seniority
Senior
Job Description
Senior System Software Engineer – Dynamo-Triton Inference Server
NVIDIA
• Develop world-class GPU-accelerated AI inference serving software • Contribute to feature development and drive broad customer adoption • Drive the convergence of the Triton Inference Server and NVIDIA Dynamo stacks to establish a unified, high-performance inference platform • Ensure feature parity and effectively serve both Large Language Model (LLM) and non-LLM workloads • Build robust software designed to be deployed in production server or cloud environments • Optimize and balance prediction throughput and latency • Develop and adopt the next generation of inference technologies
Job Requirements
- MS or PhD in Computer Science or relevant field (or equivalent experience)
- 5+ years of professional experience working on deep learning software
- Excellent Rust & C++ skills
- Familiarity with Python
- Strong programming & software design skills including debugging, performance analysis, and test design
- Experience with high-scale distributed systems and ML systems
- Strong communication skills and ability to work in a fast-paced, agile team environment
Benefits
- equity
- benefits
Related Guides
Related Job Pages
More Full-stack Engineer Jobs
• Design, build, maintain and extend products, features, and functionality that solve real customer problems • Partner with Product, Design, and Engineering to discover and validate customer needs and technical approaches • Develop and extend integrations with onboard hardware devices such as headsign controllers, passenger counters, and fareboxes • Build and improve cloud-native backend services that manage device configuration, process telemetry data, and provide observability into fleet-wide device health • Implement and maintain robust mechanisms for over-the-air software deployment, configuration updates, and remote device management • Design testing strategies that account for the realities of hardware-in-the-loop systems including integration testing, simulated environments, and production monitoring • Maintain and improve our physical hardware lab if local to San Francisco, else contribute to solutions for remote development, testing, and debugging needs • Consistently deliver incremental value by anticipating dependencies, breaking down work, and regularly demoing progress • Communicate technical trade-offs, present system design proposals clearly, and document architectural decisions • Uplevel teammates through code reviews, pairing, and strong collaboration • Take ownership of your code and product domain, engaging in retrospectives and continuously improving how the team works
• Help establish the technical foundation for a new Canada pod, including architecture, engineering practices, and delivery approach. • Extend and adapt existing US-supported capabilities for the Canadian market, including changes across frontend experiences, backend systems, business logic, and operational workflows. • Partner with Product, Design, Data, Finance, Operations, and engineers across Fullscript to translate business opportunities into practical technical solutions. • Work across the stack to deliver maintainable, observable, and scalable solutions. • Contribute to solution design, rollout planning, and measurement of business impact. • Write high-quality code, contribute to technical improvements, and maintain strong quality standards. • Help create a strong team culture by modeling ownership, collaboration, and thoughtful technical judgment. • Make build vs adapt decisions to shape how the Canada platform evolves.
Senior Full-Stack Mobile Systems Analyst
Riachuelo🌎 Viva a carreira que se conecta com @vc em nosso Ecossistema. Clique na aba "vagas" e confira nossas oportunidades! ↓
• Develop and enhance high-performance, scalable Web (React) and Mobile (React Native) applications; • Design, structure and maintain BFFs (Backend-for-Frontend) in Node.js, establishing patterns, best practices and technical guidelines; • Perform technical evaluations of proposed solutions, identifying risks, impacts, dependencies and viable alternatives; • Design solution architectures, considering integrations, data flows, non-functional requirements (NFRs) and AWS Cloud best practices; • Support the definition of integrations with internal APIs, AWS API Gateway and complementary services; • Lead quality initiatives, ensuring adequate test coverage (unit, integration, E2E); • Conduct technical code reviews with a focus on quality, security and adherence to standards; • Define observability strategies (APM, logs, metrics, distributed tracing) using Datadog, Kibana and Grafana; • Support decisions related to authentication and authorization (OAuth, OAF, OpenID Connect); • Actively and influence participatively in refinements, bringing technical vision, estimates, risks and solution alternatives; • Serve as a technical reference within the team, mentoring mid-level and junior developers, promoting best practices and technical growth; • Collaborate with Product Owner and UX to translate business needs into robust functional and technical solutions; • Coordinate technical alignments between squads and partner areas, promoting standardization and architectural consistency; • Lead incident investigations with root cause analysis (RCA), proposing preventive and corrective actions; • Support the evolution of CI/CD pipelines and automation practices; • Ensure good governance, security and cost optimization practices in AWS; • Implement serverless solutions and modern architectures focused on modularity, observability and resilience; • Document architectures, technical decisions, business flows, APIs and adopted standards; • Contribute to the creation and evolution of internal documentation (playbooks, guides, templates).
Staff Software Engineer
OptroHeadquartered in Wilmington, Delaware, Optro, founded in 2014, is a technology company that provides an AI-powered governance, risk, and compliance (GRC) platfo
• Build and ship product features end-to-end • Ability to write clear and well defined design documentation • Mentor fellow engineers • Lead application architecture decisions • Troubleshoot, debug and resolve software bugs • Implement back-end APIs in Node.JS • Work on our Ember SPA front-end • Collaborate with engineers, designers, and product managers • Participate in an Agile software development life cycle • Write well-designed, maintainable & testable code • Be product-minded and think about the customer • Contribute to open-source projects



