דרושים » תוכנה » AI Framework Software Engineer, Performance Optimizations

As an ML Software Engineer with a focus on low-level and CUDA-based optimizations, you will play a key role in shaping the design, performance, and scalability of our companys machine learning inference systems. Youll work on deeply technical challenges at the intersection of GPU acceleration, systems architecture, and ML deployment.
Your expertise in CUDA, C/C++, and performance tuning will be crucial in enhancing runtime efficiency across heterogeneous computing environments. Youll collaborate with designers, researchers, and backend engineers to build production-grade ML pipelines that are optimized for latency, throughput, and memory use, contributing directly to the infrastructure powering our company's next-generation AI products.This role is ideal for an engineer with strong systems-level thinking, deep familiarity with GPU internals, and a passion for pushing the boundaries of performance and efficiency in machine learning infrastructure.
Responsibilities
Design and implement highly optimized GPU-accelerated ML inference systems using CUDA and low-level parallelism techniques
Optimize memory, compute, and data flow to meet real-time or high-throughput constraints
Improve the performance, reliability, and observability of our inference backend across diverse compute targets (CPU/GPU)
Collaborate with cross-functional teams (including researchers, developers, and designers) to deliver efficient and scalable inference solutions
Contribute to ComfyUI and internal infrastructure to improve the usability and performance of model execution flows
Investigate performance bottlenecks at all levels of the stack-from Python to kernel-level execution
Navigate and enhance a large, complex, production-grade codebase
Drive innovation in low-level system design to support future ML workloads.

We are looking for a Senior Network SW Engineer to join the SW group and take a major part in redefining the future of AWS cloud.
Were searching for engineers with a passion for networking to develop SRD (Scalable Reliable Datagram). SRD is a high-performance, low-latency transport protocol used within our Web Services (AWS) infrastructure to optimize network performance. SRD powers several high-impact, cutting-edge products, including on-demand ML and HPC platforms leveraging EFA, next-generation storage services built on EBS, and the future of AWS network traffic.
Key job responsibilities
As a Senior Network Software Engineer on SRD team, your primary role will be to develop and optimize the implementation of SRD technology across AWS's network infrastructure. Your responsibilities will encompass designing, deploying, and maintaining SRD code-base, ensuring its reliability and scalability to accommodate the demands of various applications. An essential part of your role will involve conducting extensive network simulations to evaluate system performance under different conditions, enabling you to identify potential bottlenecks and inefficiencies. Using these simulations, you will troubleshoot network issues and implement robust solutions, leading to minimal data loss and latency. Leveraging your in-depth understanding of network protocols and AWS infrastructure, you'll refine and improve the SRD system's performance. Furthermore, you will be expected to mentor junior team members, leading projects to advance the SRD capabilities within the AWS environment. Staying updated with the latest industry trends and incorporating them into strategic network service planning.

We are looking for a JAVA Expert to join our new product initiative in data processing and analysis infrastructure.
We are the data platform company for the AI era. We are building the enterprise software infrastructure to capture, catalog, refine, enrich, and protect massive datasets and make them available for real-time data analysis and AI training and inference. Designed from the ground up to make AI simple to deploy and manage, We take the cost and complexity out of deploying enterprise and AI infrastructure across data center, edge, and cloud.Our success has been built through intense innovation, a customer-first mentality and a team of fearless who leverage their skills & experiences to make real market impact. This is an opportunity to be a key contributor at a pivotal time in our companys growth and at a pivotal point in computing history.
Location: Tel Aviv / Haifa - Israel.

We are recruiting an MLOps / AI-Ops Engineer to join our data & AI Division in Haifa.
This role is responsible for managing, optimizing, and scaling the organizations AI/ML infrastructure across both cloud and on-prem environments, ensuring high availability, performance, and cost efficiency.
Role Overview:
* Manage day-to-day AI infrastructure operations, ensuring reliability, performance, and scalability.
* Deploy, configure, maintain, and troubleshoot AI platforms and tools, including GPU orchestration, Kubernetes, MLflow/Kubeflow, and vector databases.
* Monitor resource utilization (CPU, GPU, memory, Storage, network) and implement performance optimizations.
* Support CI/CD pipelines and infrastructure automation using Infrastructure as Code (Terraform, Ansible).
* Implement security best practices, manage access control, and ensure compliance with AI governance policies.
* Troubleshoot operational incidents and collaborate with AI Platform and AI Security Engineers.
* Contribute to documentation, runbooks, and knowledge sharing.
* Identify opportunities to improve AI infrastructure processes and tooling.

We are looking for a Senior Software Engineer to join our growing team!
This is a great opportunity to be part of one of the fastest-growing infrastructure companies in history, an organization that is in the center of the hurricane being created by the revolution in artificial intelligence.