דרושים » הנדסה » Senior AI Software Development Engineer, TensorRT-LLM

We are now looking for a TensorRT-LLM Software Development Engineer!
we are hiring software engineers for its TensorRT-LLM team. Academic and commercial groups around the world are using GPUs to power a revolution in deep learning-powered AI, enabling breakthroughs in areas like LLM, ChatGPT and Generative AI that have put DL at the iPhone moment for AI. Join the team which is building the inferencing software which is foundational to product lines within our company and across the industry! The ability to work on a fast-paced delivery-focused team is required and excellent interpersonal skills are a must.
What you'll be doing:
Craft and develop robust inference software that can be scaled to multiple platforms for functionality and performance
Performance analysis, optimization, and tuning for Large Language Models (LLMs)
Conduct unit tests and performance tests for different stages of the inference pipeline.
Closely follow academic developments in the field of artificial intelligence and feature update TensorRT-LLM
Write safe, scalable, modular, and high-quality (C++/Python) code for our core backend software for LLM inference.
Collaborate across the company to guide the direction of deep learning inference, working with software, research and product teams.

We are looking for an AI Test Architect joining E2E Verification group to profile Innovative large scale Distributed training on our AI End-to-End solutions in a large scale supercomputing clusters. Provide insights on at-scale system design and tuning mechanisms for large-scale compute runs. You will work with the latest Accelerated Computing and Deep Learning software and hardware platforms, with researchers, developers, and customers to craft improved workflows and develop new, leading differentiated solutions. You will interact with HPC, OS, Switch, HCA, CPU and GPU compute, and systems specialist to architect, develop and bring up large scale performance platforms.

What youll be doing:

Profiling, benchmarking, and analyzing deep learning models to identify areas for optimization and improvement in terms of performance, efficiency, and accuracy, with a strong emphasis on networking aspects.

Collaborating closely with data scientists, researchers, development, automation teams to design and implement scalable training pipelines and frameworks that demonstrate large scale high -performance networking capabilities.

Staying up-to-date with the latest advancements in deep learning algorithms, architectures, our GPU technologies, and high-performance networking solutions.

Optimizing deep learning models for performance, memory usage, and power efficiency while maximizing high-performance networking features on our supercomputers.

Providing insights and recommendations based on the analysis of large-scale training results, specifically focusing on networking bottlenecks and optimizations, to improve model outcomes and achieve business objectives.

Collaborating with hardware engineers to guide the development and integration of efficient networking solutions for deep learning, including exploring network architecture optimizations and bringing to bear technologies such as RDMA or InfiniBand.

We are seeking a highly motivated Embedded Software Team Leader to own the execution of key components within the DPU BMC system. Seeking a candidate proficient in software development of embedded systems, taking ownership for team's tasks. Collaborate with team leaders, various teams, and customers to improve our product.


What you'll be doing:

Lead and manage a team of embedded software engineers, providing both personal and professional mentorship.

Drive the execution of assigned components from conception to delivery, ensuring timely software milestones and contributing to overall product releases.

Coordinate with peer team leaders to ensure seamless integration across the broader DPU system.

Engage in hands-on embedded software development using C/C++.

Establish and lead all developments and methodology aspects and process.

Take ownership for delivering functionality, stability, and performance of the system.

Collaborate closely with internal cross-functional teams and peer leaders (architecture, hardware, firmware, validation, product management).

Work directly with external customers to understand system requirements, use cases, and provide technical support.

We seek a highly motivated Network Performance Exploration Engineer to join our team of experts and help shape the foundational infrastructure for the AI revolution. Our next-generation networking systems are at the forefront of connecting and powering the world's most advanced AI clusters. As a key member of our architecture team, you will be responsible for exploring and identifying critical network optimization opportunities across our entire hardware and software stack, analyzing how system-level changes impact application-level performance.
What Youll Be Doing:
Explore and validate end-to-end application performance, defining comprehensive test plans and critical metrics to identify optimization opportunities in both hardware and software.
Establish and maintain a comprehensive database of benchmark results, tracking performance across releases to drive data-informed decisions.
Conduct deep-dive analysis into communication libraries (like NCCL), system software, and hardware configurations to investigate performance characteristics, validate architectural theories, and identify bottlenecks.
Provide critical performance data to correlate and enhance simulation tools, ensuring our models accurately predict real-world hardware behavior.
Analyze application-level traffic patterns (e.g., LLMs) on our advanced networking fabrics to identify hardware and software optimization opportunities and tune system parameters.
Lead Proof-of-Concept (POC) projects to prototype and evaluate potential hardware and software optimizations and their impact on application performance.

Join the AI & Automation Supply Chain Business Transformations team in our Operations to architect the future of agentic AI at scale. We Implement AI agents to transform employee productivity and accelerate business impact. As the senior systems architect in Operations, you implement our vision for codifying our decision logics, decision intelligence, AI agent design, build and deployment, integration, security, and lifecycle management, ensuring the AI Agents delivers value that are trusted, scalable, and innovative. This is a rare opportunity to define the AI agents for Supply Chain Operations inside one of the worlds most advanced AI companies. If you thrive at the intersection of AI innovation, and Supply Chain transformation, join us and make your mark on the future of agentic AI.

What you will be doing:

Capture business requirements, translate requirements into functional design, user stories, technical design, drive end to end integration testing, support data set up and issue remediation during UAT, manage development team activities, develop hypercare support model

Define and architect AI agents for Supply Chain use cases, using the right frameworks, multi-agent coordination, RAG, deployment, monitoring, and life cycle management.

Be hands on in quick proof of concepts development to demonstrate technical feasibility and implement enterprise grade Agentic Supply Chain solutions

Partner with Enterprise IT engineering, product, and research teams while evaluating LLMs, agentic frameworks, and our own NeMo technologies.

Ensure integration with enterprise IT and Operations data sources and Industrys best Agentic platforms with strong content security focus.

Drive architectural decisions across deployment models (on-prem, cloud, hybrid, containerized) to deliver scalable, reliable, and efficient solutions.

Lead design reviews, develop technical documentation, and guide developers in principles of architecture and code development.

Champion observability, monitoring, versioning, and telemetry to ensure trustworthy and auditable AI agents.

Influence Supply Chain Operations adoption of the platform by partnering with stakeholders across IT, supply chain and serve as a reference adopter providing feedback to strengthen our ecosystem.

We are looking for a versatile Senior Software Engineer to join our DPU Platform team. This is an opportunity to make a significant impact in a technology-driven company that powers the worlds most advanced data centers. You will use your expertise in low-level embedded Linux software and boot flows to work with global development teams, solving the complex challenges involved in delivering high-power computing platforms.

What you'll be doing:

Designing and developing low-level system software with a primary focus on bootloaders (ATF, UEFI), firmware, and hardware initialization.

Working together with hardware and design teams to drive SoC bring-up and platform enablement.

Solving complex challenges related to boot sequences, system optimization, and hardware resource management.

Supporting various internal and customer DPU projects alongside our global teams.

Taking part in all stages of the product lifecycle, with a focus on high software quality and stability.

Collaborating within a global software environment to have a broad impact across the company.

Our Networking Research group is seeking a forward-thinking Engineering Manager with a product leadership approach to manage a team of Software Engineers, AI Agent Developers, and Researchers.

In this role, you will bridge the gap between brand-new AI research and practical engineering. You will lead the charge in integrating autonomous AI agents into the daily workflows of our architects, hardware designers, and researchers. You will be responsible for understanding internal engineering bottlenecks, researching the latest academic and industry advancements, and translating them into deployed production tools using our AI stack.

What you'll be doing:

Team Leadership & Strategy: Lead and mentor a mixed team of SW engineers and researchers, balancing the agility of research with the responsibility of production software engineering.

Product Engineering: Partner with internal engineering teams (Hardware, Architecture, Research) to analyze their workflows, identify friction points, and architect Agentic AI solutions to accelerate their work.

Applied Research: Actively monitor the latest AI trends, academic papers, and technical blogs (LLMs, Agents, RAG). Translate these insights into concrete features and tools for the team.

Agent Architecture: Be responsible for the design of scalable frameworks for AI agent interaction, ensuring they can reason, plan, and orchestrate tasks within complex engineering environments.

SW-Focused MLOps: Define and implement the software lifecycle for AI models - from fine-tuning to deployment - utilizing our AI deployment tools and ensuring seamless CI/CD.

Production Deployment: Ensure reliable operation of agent fleets, optimizing for latency and resource consumption while maintaining security and access controls.

We are looking for a Test Development Engineer to join our team. This role will work as part of a team driven by the development of our company's networking and interconnect products. Do you have a passion for automation development, test program development, code writing and looking for sophisticated and significant topics? We will be happy to have your skills on the team. You will handle various projects across teams, build test plans, automate test specification and execution. You will continuously innovate and develop scalable, reliable, high-performance systems and tools to enable the next generation of Interconnect products.
What Youll Be Doing:
Will work on projects across multiple functional teams from different geographies throughout the product lifecycle
Develop test plans, and execute testing via automation and manually for all supported hardware releases
Work with cross-functional teams across engineering, thermal, mechanical, and HW to identify test requirements
Develop automation and tools for our company hardware releases and test environment
Debug HW & SW failures in interconnect products, Isolate the problem, and get to the root cause
Design and build technical processes to address business issues
Deploy the test solution to the production sites and provide support if needed.
Train personnel on the required processes and operations of complex test systems.
Ensure all testing is being conducted in compliance with all safety protocols.

We are looking for a skilled Test Development Engineer to join our diverse team focused on developing the test framework and tools for our company's networking and Interconnect products. As a technical focal point, you will collaborate across multiple teams, taking ownership of test suite development, specifications, tools, and automation. You will be a resource in driving innovation and developing scalable, reliable, and high-performance Software that enables the next generation of interconnect technologies. If youre passionate about code development, automation, innovation in testing programs, and becoming a key technical contributor, wed love to have you on board!
What Youll Be Doing:
Collaborate with multi-functional teams including, operation, thermal, mechanical, and hardware to define and refine test requirements
Take the lead in identifying and resolving hardware and software failures, guiding the team to pinpoint root causes
Lead all aspects of deployment of test solutions to production environments and ensure smooth integration and support when required
Develop comprehensive testing software and automation tools for hardware releases
Act as the go-to guide for developing sophisticated test systems, provide mentoring and guidance to other experts and technical staff.

The company Networking Advanced Development Software team develops new groundbreaking technologies to enable new market shares for the company and tighten customer relationships. These are emerging technologies in networking and distributed computing for the booming AI factories and data centers. They span areas such as AI neural networks, Deep Learning, High Performance Computing (HPC), Storage, Cloud, SW Defined Network, Network Function Virtualization, 5G NR and more. We develop the solutions top-down, all the way from application behavioral analysis, to architecture definition and down to the implementation, using the world-leading company devices. The development traverses any needed component - application SW, middleware SW, OS kernel subsystems, device drivers, embedded SW (Firmware) and CUDA GPU. We collaborate with partners and key customers in the analysis processes and engage with open source communities introducing our leading features.
What youll be doing:
Lead a team of 5 engineers in the advanced technologies development
Design and implement solutions throughout all layers from high level application, OS and driver subsystem to firmware
Work on impactful projects involving state-of-the-art high-performance computing hardware and software
Provide insight and technical guidance and collaborate with peers from across the company - including software architecture, chip architecture, and engineering departments to improve our future technology
Collaborate with our company partners and customers.