Algorithm Engineer - Deep Learning

KLA•Milpitas, CA

1d•Onsite

About The Position

KLA is a global leader in diversified electronics for the semiconductor manufacturing ecosystem. Virtually every electronic device in the world is produced using our technologies. KLA invents systems and solutions for the manufacturing of wafers and reticles, integrated circuits, packaging, printed circuit boards and flat panel displays. The innovative ideas and devices that are advancing humanity all begin with inspiration, research and development. KLA focuses more than average on innovation and we invest 15% of sales back into R&D. Our expert teams of physicists, engineers, data scientists and problem-solvers work together with the world’s leading technology providers to accelerate the delivery of tomorrow’s electronic devices. Life here is exciting and our teams thrive on tackling really hard problems. There is never a dull moment with us. With over 40 years of semiconductor process control experience, chipmakers around the globe rely on KLA to ensure that their fabs ramp next-generation devices to volume production quickly and cost-effectively. Enabling the movement towards advanced chip design, KLA's Global Products Group (GPG), which is responsible for creating all of KLA’s metrology and inspection products, is looking for the best and the brightest research scientist, software engineers, application development engineers, and senior product technology process engineers. The Broadband Plasma Division (BBP) provides market-leading patterned wafer optical inspection systems for leading-edge IC manufacturing. Logic, foundry, and memory customers depend on BBP products to detect yield-critical defects for process debug and excursion monitoring at advanced process nodes. BBP flagship products include the 29xx and 39xx series which leverage Broadband Plasma technology to capture a wide range of defects with ultimate sensitivity at the optical inspection speeds needed for inline defect monitoring.

Requirements

Ph.D. in Electrical Engineering, Computer Science, or related quantitative fields.
Academic or industrial experience applying deep learning or GenAI to real-world problem(s), with impactful results.
In-depth experience developing and optimizing deep learning, Vision Foundation Models (VFM), or Vision Language Models (VLM) in at least one of the following areas: computer vision, image processing, robotics, NLP, or equivalent, with strong emphasis on efficiency, scalability, and deployment performance.
Required experience with DL model optimization/distillation for mixed or reduced precision (e.g., FP16, FP8) to improve throughput, latency, and deployment efficiency.
Experience with GenAI coding tools, vibe coding , or vibe engineering.
Proficiency in Python and one additional programming language from: C++, Java, Rust, Go.
Proficiency in at least one deep learning framework (e.g., PyTorch, TensorFlow, JAX, or equivalent).
Demonstrated deep learning expertise via technical publications in top conferences (e.g., NeurIPS, CVPR, ICML, ICLR, KDD, SIGGRAPH, etc.) and/or industrial patents and/or impactful open-source projects is required.
Academic or industrial experience applying deep learning or GenAI to real-world problem(s), with impactful results.
Required experience with DL model optimization/distillation for mixed or reduced precision (e.g., FP16, FP8) to improve throughput, latency, and deployment efficiency.

Nice To Haves

Experience in semiconductor process control is a plus.

Responsibilities

Understand state-of-the-art (SOTA) deep learning and GenAI models.
Connect SOTA DL modeling approaches to domain problem statements.
Analyze modeling requirements based on product feature requirements.
Design deep learning and GenAI models to meet modeling requirements.
Implement modeling prototypes and perform analysis.
Perform model training and/or tuning on domain datasets.
Evaluate and validate model performance against defined metrics.
Analyze model performance bottlenecks.
Design and optimize DL model architectures, including new modules, efficient backbones, and model compression techniques (e.g., distillation).
Optimize DL or GenAI model throughput and cost, including mixed-precision and low-precision inference and training (e.g., FP16, FP8).
Work and communicate collaboratively with peers.
Present ideas, concepts, and results in professional technical settings.