דרושים » הנדסה » Applied AI Scientist - On Site

We are seeking a highly motivated Senior Deep Learning Researcher to join our team! This is an outstanding opportunity to conduct impactful research and develop the next generation of large language model (LLM) inference algorithms. You will work on technologies that directly enhance our software, making the latest LLMs more efficient and accessible for users worldwide.

By joining us, you will be part of a strategic effort to establish us as the definitive platform for high-performance LLM inference. You will engage with our skilled problem-solvers and top organizations, crafting AI technology advancements.

What you'll be doing:
Research, invent, and implement groundbreaking algorithms for LLM inference to advance the state of the art in both low-latency and high-throughput scenarios.

Translate research into practical software solutions that directly impact our products and customers.

Collaborate with internal research, engineering, and product teams across the globe to drive the development of advanced inference technologies.

Analyze the performance of new algorithms on our latest hardware, identifying bottlenecks and opportunities for algorithmic optimizations.

Partner with leading scientific organizations and industry pioneers to remain at the forefront of technological advancements and integrate the latest innovations into practical applications.

We seek a versatile Senior Software Engineer who is passionate about performance optimization and generative AI. Our team brings the latest research in LLM inference - from novel decoding strategies to quantization schemes - into production across our hardware lineup, from large data center servers to powerful edge devices. We work on the most advanced architectures in the field, with a focus on NVIDIA's own.

What you'll be doing:

Implement and optimize inference algorithms for LLM and omnimodal architectures, including hybrid Mamba-Transformer and mixture-of-experts models.

Profile inference pipelines using NVIDIA's profiling and simulation tools. Correlate simulation predictions against real hardware across data center and edge devices.

Write and tune GPU kernels (CUDA, Triton) for operators like fused MoE layers, SSM state updates, and quantized GEMMs.

Solve distributed inference problems: expert parallelism, communication-compute overlap, collective tuning, multi-node deployment.

Build production-grade software inside major open-source libraries - vLLM, SGLang, Dynamo, FlashInfer.

Own optimization features end-to-end, from scoping through delivery, collaborating with research, product, and engineering teams worldwide.

a rapidly growing startup company, developing the next-generation smart-infrastructure solution based on novel fiber-sensing technology (smart roads, smart cities, perimeters, and grid monitoring, etc.). The company offers an award-winning disruptive solution; a sensor free approach to smart infrastructure. The company is VC backed and in the revenues stage. Combining pioneering technology in optical fiber sensing with state-of-the-art Machine Learning, we help prevent environmental disasters, protect human lives, and keep critical energy and transportation backbones running smoothly. We are looking for a talented, self-driven, and hands-on DSP Researcher to join our Photonics R&D team. In this role, you will research and develop next-generation distributed fiber-optic sensing technologies, focusing on signal processing, system modeling, simulations, and experimental validation. Working at the intersection of physics, electro-optics, fiber-optic sensing, and DSP, you will transform complex physical phenomena into robust sensing solutions for real-world applications. You will tackle challenging physical and algorithmic problems, contribute to cutting-edge sensing products, and collaborate closely with multidisciplinary R&D teams. This role is ideal for someone who thrives in a fast-paced environment, enjoys working across disciplines, and is excited to take ideas from research and lab validation to large-scale deployment.
 
What Youll Do:
* Conduct experimental and theoretical R&D for next-generation distributed fiber-optic acoustic sensing systems.
* Develop, implement, and validate DSP algorithms for coherent optical sensing systems.
* Build end-to-end expertise across the full sensing pipeline, including optical signal generation and propagation, coherent detection, signal acquisition, DSP, and advanced data analysis.
* Design and run laboratory experiments to validate new concepts, improve system performance, and support current and future product generations.
* Develop simulations, models, and analysis tools using Python and/or C ++ for lab experiments, field data analysis, signal processing, and system -level performance evaluation.
* Work with field experiment data to identify performance gaps, validate models, and improve sensing capabilities.
* Collaborate with R&D teams across disciplines to develop, validate, and integrate new sensing capabilities.
* Communicate complex technical concepts clearly to both technical and non-technical stakeholders.

The MLIL DataPlane team is looking for a Senior Software Development Engineer to own the design and implementation of our inference data plane. We build the software that makes large models run efficiently on custom hardware - spanning model execution, memory management, data movement, and serving integration.
Our work covers the full inference path: integrating serving engines with custom hardware, developing high-performance compute kernels, enabling efficient data movement, and driving models from early validation through production. We operate at frontier scale with large distributed models.
This is a ground-up effort with rapidly evolving hardware and software. We need a senior IC who can write and optimize low-level code for custom hardware, validate model architectures end-to-end, build test and profiling infrastructure, and drive performance across the stack.

Key job responsibilities
- Develop and optimize compute kernels for a custom ML accelerator architecture, targeting production-level performance for large language model inference.
- Implement and validate LLM architectures (decoder-only, mixture-of-experts) end-to-end - from PyTorch model definition through distributed execution on custom hardware.
- Integrate custom accelerator backends into open-source ML serving frameworks (vLLM, PyTorch), including scheduler extensions, memory management, and model parallelism.
- Build and maintain test infrastructure for model correctness validation across CPU, GPU, simulator, and hardware targets.
- Profile and optimize inference workloads - identify bottlenecks, instrument critical paths, and drive latency and throughput improvements from simulation through hardware bringup.
- Own features end-to-end: from design through implementation, testing, and integration into the broader software stack.
- Contribute to CI/CD pipelines that gate model and kernel changes on correctness and performance regressions.
- Mentor engineers, drive design reviews, and raise the engineering bar across the team.

Our breakthrough World Model technology combines aerial imagery with real-time ground views to build an accurate, rich representation of the vehicle's environment. As part of our World Modeling team, you will drive the next generation of AI-powered, cloud-defined vehicle technology-tackling ambitious research and turning cutting-edge deep learning into real-world solutions.

Responsibilities
Research, design, and implement state-of-the-art deep learning models in computer vision (e.g., detection, segmentation, transformers, self-supervised learning).
Translate research into production-ready algorithms, writing clean, efficient, and scalable code in Pytorch.
Explore creative ideas, experiment with novel architectures, and continuously push beyond current SOTA.
Take ownership of your work end-to-end, from concept through prototyping to deployment in production.

We are looking for a Software Development Engineer to own the design and implementation of our inference data plane. We build the software that makes large models run efficiently on custom hardware - spanning model execution, memory management, data movement, and serving integration.
Our work covers the full inference path: integrating serving engines with custom hardware, developing high-performance compute kernels, enabling efficient data movement, and driving models from early validation through production. We operate at frontier scale with large distributed models.
This is a ground-up effort with rapidly evolving hardware and software. We need an individual contributor who can write and optimize low-level code for custom hardware, validate model architectures end-to-end, build test and profiling infrastructure, and drive performance across the stack.

Key job responsibilities
- Develop and optimize compute kernels for a custom ML accelerator architecture, targeting production-level performance for large language model inference.
- Implement and validate LLM architectures end-to-end - from PyTorch model definition through distributed execution on custom hardware.
- Integrate custom accelerator backends into open-source ML serving frameworks (vLLM, PyTorch), including scheduler extensions, memory management, and model parallelism.
- Build and maintain test infrastructure for model correctness validation across CPU, GPU, simulator, and hardware targets.
- Profile and optimize inference workloads - identify bottlenecks, instrument critical paths, and drive latency and throughput improvements from simulation through hardware bringup.
- Own features end-to-end: from design through implementation, testing, and integration into the broader software stack.
- Contribute to CI/CD pipelines that gate model and kernel changes on correctness and performance regressions.

Our Network Architecture, Modeling and Performance Insights group is seeking a skilled and driven hands-on Network Modeling Architect to conduct advanced network research and optimization while utilizing and enhancing our advanced simulation tools.

In this role, you will be a key contributor to defining the architecture and improving network performance for AI and High Performance Computing (HPC) workloads. You will be responsible for modeling advanced network topologies, configurations, logic and traffic patterns, and analyzing their effect on end-to-end performance. You will develop expertise in our simulation tools and write code daily to contribute directly to their development road map and prioritization, develop core features in the simulator, and expose the capabilities to additional users. You will take part in complex architecture decisions, define and verify the modeling assumptions, and put them to the test vs. real HW and SW performance. If you're passionate about tackling intricate challenges and contributing to comprehensive systems and working on innovative solutions, we want to hear from you.

 

What you'll be doing:

Analyze and model our AI and High Performance Computing offerings, deep dive into network behavior for training and inference and generate insights to directly impact the architecture of next-generation of AI systems. Conduct advanced network modeling, research and optimization using innovative simulation tools.

Write production-quality C++ and Python code daily. Hands-on modeling of advanced network topologies, configurations and traffic patterns representing real life AI workloads, and analyze their effect on the system's performance. Actively develop the simulator software solution while contributing modular and scalable code.

Actively support the HW and SW development life cycles, map existing and candidate features into the simulation domain to enable their analysis, impact assessment and optimization.

Take full independent ownership of the performance modeling roadmap for a defined set of features. Interface directly with internal clients, communicate the analysis conclusions effectively and iterate on them. Drive projects from concept to completion.

Improve the quality of the simulation as a software product, ensuring robustness and reliability.

At UVeye, we're on a mission to redefine vehicle safety and reliability on a global scale. Founded in 2016, we pioneered the world's first fully automated suite of AI-powered vehicle inspection systems, combining computer vision, machine learning, and generative AI.
With over $380M in funding and strategic partnerships with Toyota, Amazon, General Motors, JLR, Volvo, and Hertz, our technology is deployed across manufacturing plants, dealerships, wholesale auctions, fleets, and seaports worldwide. Named one of Fast Company's Most Innovative Companies of 2026, our 300+ global employees are solutions-oriented, accountable, and driven by one shared goal: making roads safer for everyone.
We are looking for an experienced Research Scientist, Sensing to push UVeye’s inspection beyond today’s sensing stack. You will evaluate, prototype, and develop AI models for new sensing modalities such as thermal, hyperspectral, acoustic, radar, structured light, and event cameras, surfacing vehicle defects that today’s systems cannot see.
A day in the life and how you’ll make an impact
* Survey emerging sensing technologies and identify the modalities most likely to expand UVeye’s defect coverage.
* Prototype with new hardware, build small-scale datasets from scratch, and train modality-specific models.
* Run controlled experiments that benchmark new modalities against today’s inspection stack on shared defect scenarios.
* Develop multi-modal fusion approaches that combine new and existing sensors for stronger detection.
* Recommend which modalities graduate into product and partner with R&D and product on integration.

Req ID: 29153

As a Senior Machine Learning Scientist, you will work closely with engineers and product to design, develop, evaluate and deploy Gen AI powered solutions for scalable, customer-facing applications. Your work will focus on applying state-of-the-art agentic capabilities and driving business impact based on rigorous evaluations and experimentation.


Key Job Responsibilities and Duties:

Design end-to-end agentic systems, delivering high-quality, performant, and efficient solutions to production

Build agentic solutions for different tasks and use cases using state-of-the-art techniques

Develop and carry out evaluation strategies, including formulating new metrics and building evaluation judges

Pioneer and promote best practices and adoption of new technology in GenAI application development

Lead and mentor other team members, providing technical guidance and timely feedback to develop the team and motivate them to achieve their goals.

Collaborate with product managers, data scientists, and analysts to understand business requirements and translate them into ML solutions.

Conduct deep data analysis to evaluate model performance, label quality, features exploration.

Work closely with ML engineers to ensure and improve the solutions latency/throughput meets product requirements and ensure deployment of your model to production.

We are seeking a Director of Software Architecture to lead and accelerate the evolution of next-generation AI data center and networking technologies. This role is designed for a hands-on, execution-driven leader who pushes boundaries, translates vision into reality, and delivers high-impact solutions at scale. You will operate at the intersection of innovation, architecture, and delivery-shaping the future of AI networking and infrastructure.

What you will be doing:
Drive identification, evaluation, and rapid adoption of emerging technologies, ensuring strong alignment with strategic roadmap and measurable business outcomes.
Lead the design and delivery of advanced networking applications, leveraging data plane programming and modern networking protocols to solve complex, large-scale challenges.
Architect solutions across AI data center environments, integrating GPU-based systems, hardware acceleration, and high-performance networking.
Act as a thought leader and industry influencer-engaging directly with customers, publishing technical content, and representing us at key conferences and forums.
Define and execute a bold architectural vision for our networking in close collaboration with cross-functional software and hardware leaders.