Experience:

• 5+ years of experience
• 5+ years of proficiency in application development using C#, Java, or another programming language
• Exposure to at least one scripting language such as Python, Perl, or PHP
• Strong analytical and problem-solving abilities
• Ability to multitask effectively in a dynamic environment
• Experience with databases and SQL
• Experience working with source control systems and CI/CD pipelines
• Outstanding written and oral communication skills

Qualification:

• B.Tech or higher degree in Computer Science, Information Technology, Software engineering, or related field

Responsibilities:

• Design, implement, and maintain robust infrastructure for AI workloads
• Run AI workloads through inference backends such as Llama.cpp, Ollama, Pytorch, WinML, TRT-RTX, and others
• Scope requirements for deploying AI applications, benchmarks, and models in automation
• Develop solutions to measure accuracy, functionality, and performance
• Build infrastructure to download AI models from various sources and manage a local repository
• Create automated synchronization to keep the repository up to date
• Analyze large datasets to derive insights
• Design visualizations for developer review
• Implement data processing engines to transform raw data into usable formats
• Collaborate with Local AI developers to add automation features that help debug and isolate issues
• Design, implement, and maintain CI/CD pipelines for automated build and deployment
• Collaborate with development teams for seamless integration and deployment
• Understand existing infrastructure and debug issues in current frameworks
• Identify performance bottlenecks and devise efficiency improvements

Nice to have:

• Experience building robust backend automation systems with hands-on database work
• Experience setting up visualization interfaces using Grafana, Kibana, or similar platforms
• Hands-on background with git-based CI/CD pipelines, Kubernetes, and Docker
• Hands-on experience with inference frameworks such as Llama.cpp, Ollama, and PyTorch

More skills:

infrastructure, inference backends, Llama.cpp, Ollama, Pytorch, WinML, TRT-RTX, AI applications, AI models, benchmarks, accuracy measurement, functionality measurement, performance measurement, model downloading, repository management, synchronization mechanisms, data analysis, data visualization, data processing engines, debugging, issue isolation, build automation, deployment automation, databases, Grafana, Kibana, Docker

Other:

• Full time
• Job category: Engineering
• The Local AI team develops the software platform for NVIDIA client platforms including GeForce RTX PCs, RTX PRO workstations, RTX Spark, DGX Spark, and DGX Station
• The role is on the Local AI Automation team
• The company values diversity and is an equal-opportunity employer
• Competitive salaries and a generous benefits package
• Large and rapidly growing engineering teams
• Opportunity to work with highly qualified engineers
• Focus on building infrastructure for high-quality AI applications and models