NVIDIA is committed to fostering a diverse work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.
Senior Software Engineer, AI Inference Systems
Location
Poland
Posted
77 days ago
Salary
zł292.5K - zł650K / year
Seniority
Senior
Job Description
Senior Software Engineer, AI Inference Systems
NVIDIA
• Contribute features to vLLM that empower the newest models with the latest NVIDIA GPU hardware features; profile and optimize the inference framework (vLLM) with methods like speculative decoding, data/tensor/expert/pipeline-parallelism, prefill-decode disaggregation. • Develop, optimize, and benchmark GPU kernels (hand-tuned and compiler-generated) using techniques such as fusion, autotuning, and memory/layout optimization; build and extend high-level DSLs and compiler infrastructure to boost kernel developer productivity while approaching peak hardware utilization. • Define and build inference benchmarking methodologies and tools; contribute both new benchmark and NVIDIA’s submissions to the industry-leading MLPerf Inference benchmarking suite. • Architect the scheduling and orchestration of containerized large-scale inference deployments on GPU clusters across clouds. • Conduct and publish original research that pushes the pareto frontier for the field of ML Systems; survey recent publications and find a way to integrate research ideas and prototypes into NVIDIA’s software products.
Job Requirements
- Bachelor’s degree (or equivalent experience) in Computer Science (CS), Computer Engineering (CE) or Software Engineering (SE) with 7+ years of experience; alternatively, Master’s degree in CS/CE/SE with 5+ years of experience; or PhD degree with the thesis and top-tier publications in ML Systems, GPU architecture, or high-performance computing.
- Strong programming skills in Python and C/C++; experience with Go or Rust is a plus; solid CS fundamentals: algorithms & data structures, operating systems, computer architecture, parallel programming, distributed systems, deep learning theories.
- Knowledgeable and passionate about performance engineering in ML frameworks (e.g., PyTorch) and inference engines (e.g., vLLM and SGLang).
- Familiarity with GPU programming and performance: CUDA, memory hierarchy, streams, NCCL; proficiency with profiling/debug tools (e.g., Nsight Systems/Compute).
- Experience with containers and orchestration (Docker, Kubernetes, Slurm); familiarity with Linux namespaces and cgroups.
- Excellent debugging, problem-solving, and communication skills; ability to excel in a fast-paced, multi-functional setting.
Related Guides
Related Job Pages
More Full-stack Engineer Jobs
Senior Software Engineer – API Development
H1H1 is the connecting force for global HCP, clinical, scientific and research information.
• At H1, we believe access to the best healthcare information is a basic human right • Our mission is to provide a platform that can optimally inform every doctor interaction globally • This promotes health equity and builds needed trust in healthcare systems • To accomplish this our teams harness the power of data and AI-technology to unlock groundbreaking medical insights and convert those insights into action that result in optimal patient outcomes and accelerates an equitable and inclusive drug development lifecycle
Senior Software Engineer – AI, Fullstack
AgiloftThe global standard in no-code contract lifecycle management (CLM) software.
• Lead the design and development of core platform features using Python and an API-first approach • Build scalable, reliable backend services that power our applications, integrating seamlessly with a modern cloud-based architecture • Implement front-end features and help manage a growing React project in TypeScript • Collaborate with design and product teams to ensure that what we’re building is scalable, maintainable, and secure • Contribute to infrastructure and deployment workflows in our AWS serverless environment (e.g., Lambda, API Gateway, DynamoDB) • Independently lead proof-of-concept projects and tackle complex architectural and engineering challenges • Leverage AI-assisted tools to enhance productivity, streamline workflows, and support day-to-day activities • Other duties as assigned
Senior Software Engineer
PortlessPortless fulfills e-commerce orders directly from China, shaving months of time and saving you $$$ along the way.
- Lead the design and implementation of scalable and maintainable software architectures. - Drive technical strategy and define best practices for software development across engineering teams. - Mentor and guide engineers to enhance their professional growth and technical skills. - Collaborate with product management and stakeholders to create innovative software solutions that meet business needs. - Ensure the reliability, security, and performance of Portless’ software products. - Lead code reviews and promote high coding standards and quality assurance practices. - Evaluate and integrate new technologies and tools to improve efficiency and system capabilities. - Contribute to long-term planning and roadmap development aligned with company objectives.
• Design and implement components of scalable, fault-tolerant web crawling and extraction pipelines • Write clean, production-grade code in Java and Python • Build and operate ETL/ELT pipelines for large-scale data extraction and transformation • Work with cloud infrastructure on GCP and AWS, primarily on GKE • Improve observability, reliability, and operational excellence across the systems you contribute to • Partner with product and data science teams to deliver impactful solutions • Contribute to code reviews, documentation, and knowledge sharing across the team • Stay current with evolving web technologies, anti-crawling mechanisms, and AI-powered extraction approaches
