New opportunity

Algorithm Manager

KLA · Chennai, India

About this role

This role leads a highly skilled algorithms team within the LS-SWIFT division of the GPG product group at KLA, delivering advanced real-time image processing, computer vision, and machine learning solutions that are critical to the performance and differentiation of KLA's wafer inspection products.

Responsibilities

Provide technical leadership in algorithm design and development for wafer inspection products.
Collaborate with system, product, and domain experts to define algorithm performance requirements and deliver customer-driven solutions.
Mentor and motivate engineers to solve complex technical and investigative problems.
Represent the algorithms team during system-level hardware and software integration.
Develop, validate, and deploy image processing, computer vision, and machine learning algorithms.
Support software quality and reliability activities as part of the development lifecycle.

Required qualifications

PhD in CS/EE/Math/Physics with 3+ years of experience, or MTech/MS/BTech/BS in CS/EE with 6+ years of experience.
Strong background in image processing and computer vision; working knowledge of machine learning and deep learning.
Proficient in C/C++ and MATLAB; experience on Unix/Linux platforms.
Hands-on experience with object-oriented and/or functional programming.
Strong problem-solving skills with the ability to work effectively in a fast-paced environment.
Good communication and collaboration skills with emerging technical leadership capability.

Preferred qualifications

Python and ML frameworks (e.g., TensorFlow) experience is a plus.

For full details about this role, click “Apply on company site” to view the employer’s original posting.

Skills for this role

C/C++MATLABPythonTensorFlowImage ProcessingComputer VisionMachine LearningDeep LearningUnix/Linux

Checking your profile…

Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.

Understand the role

What matters most

Algorithm Design & Development
Deliver advanced real-time image processing, computer vision, and machine learning algorithms for semiconductor wafer inspection products within the LS-SWIFT division.
Cross-Functional Collaboration
Partner with system, product, and domain experts to translate customer-driven requirements into robust algorithm performance specifications.
Technical Leadership & Mentorship
Lead, mentor, and motivate a skilled team of engineers to resolve complex investigative problems and support the full software development lifecycle.
System-Level Hardware/Software Integration
Represent the algorithms team during complex hardware and software integration activities, ensuring high reliability and performance.

Likely challenges to think through

Balancing Real-Time Processing with Algorithmic Complexity
Advanced computer vision and machine learning models must execute efficiently within high-throughput semiconductor manufacturing systems. Prepare by reviewing optimization techniques, C/C++ performance tuning, and efficient model deployment strategies.
Bridging Domain Expertise Across Hardware and Software
Navigating trade-offs between hardware constraints and software capability during system integration requires deep coordination. Prepare by highlighting past experience in cross-functional engineering teams and hardware-software co-design.

Practice your answers

Technical practice

Image Processing Techniques for Defect Detection

What to coverDiscuss how you would design an image processing pipeline for detecting fine defects on high-sample semiconductor wafers. Candidates should address filtering, edge detection, segmentation techniques, and how to handle noise while preserving critical defect features.

Real-Time Performance and Optimization in C/C++

What to coverExplain how you optimize computer vision algorithms written in C/C++ for real-time execution on Unix/Linux platforms. Discuss memory management, cache locality, multi-threading, and profiling tools.

Machine Learning vs. Traditional Computer Vision Trade-offs

What to coverWhen would you choose a classical computer vision approach over a deep learning model for wafer inspection tasks? Address trade-offs regarding computational overhead, training data availability, determinism, and explainability.

Algorithm Validation and Deployment Methodologies

What to coverDescribe your approach to validating and deploying computer vision and machine learning models in a production environment. Emphasize regression testing, robustness against variance, and tracking performance metrics.

MATLAB to C/C++ Migration and Prototyping

What to coverHow do you transition an algorithm prototyped in MATLAB into production-grade C/C++ code? Discuss code generation tools, numerical consistency checks, and performance bottlenecks during conversion.

Handling Class Imbalance in Defect Detection

What to coverIn semiconductor manufacturing, severe defect anomalies are rare compared to normal surface areas. Explain strategies to handle extreme class imbalance when training machine learning classifiers.

Hardware and Software System Integration

What to coverWhat challenges arise when representing an algorithms team during system-level hardware and software integration? Discuss synchronization, latency constraints, and interface definitions between software algorithms and hardware sub-systems.

Object-Oriented Design for Algorithm Frameworks

What to coverHow do you structure an extensible object-oriented algorithm library in C++ or Python? Focus on design patterns, modularity, and maintainability across multiple product lines.

Behavioural practice

Technical Leadership and Mentorship

What to coverDescribe a situation where you mentored an engineer to solve a complex technical problem. Use the STAR method to explain how you motivated them, guided their investigation, and ensured project success.

Cross-Functional Collaboration and Requirements Definition

What to coverTell me about a time you collaborated with system, product, or domain experts to define conflicting performance requirements. Explain how you aligned stakeholder expectations and delivered a customer-driven solution.

Managing High-Pressure System Integration Issues

What to coverGive an example of facing a critical bug or performance bottleneck during hardware and software integration. Detail your troubleshooting process, how you kept the team focused, and the final outcome.

Balancing Fast-Paced Delivery with Software Quality

What to coverDescribe a scenario where you had to balance tight delivery timelines with software reliability and quality standards. Discuss how you prioritized tasks and supported quality assurance activities.

Sharpen your knowledge

Topics to prepare

Image Processing and Computer Vision
Review core concepts in filtering, edge detection, segmentation, and feature extraction used in automated inspection systems. Relevance: Directly tied to developing and validating computer vision algorithms for wafer inspection products.
Machine Learning and Deep Learning Foundations
Refresh supervised and unsupervised learning, convolutional neural networks, and model training methodologies. Relevance: Supports the working knowledge requirement for machine learning and deep learning solutions in defect detection.
System-Level Integration and Algorithm Deployment
Study software and hardware integration principles, real-time performance constraints, and lifecycle reliability. Relevance: Aligns with responsibilities to represent the algorithms team during hardware/software integration and deployment.

Skills to revise

C/C++ and MATLAB Proficiency
Practice writing and optimizing high-performance code, memory management, and prototyping algorithms in MATLAB. Relevance: Essential for meeting the primary proficiency requirements for algorithm development on Unix/Linux platforms.
Unix/Linux Environment Operations
Brush up on shell scripting, process management, and debugging tools in Unix/Linux. Relevance: Required for deploying and validating algorithms on Unix/Linux production platforms.
Python and TensorFlow Frameworks
Build small neural network prototypes using Python and TensorFlow. Relevance: Addresses the preferred qualifications for modern machine learning frameworks.

Your preparation checklist

Review Core Image Processing and Computer Vision Concepts
Refresh fundamental techniques in filtering, edge detection, segmentation, and feature extraction. Completion means you can explain how these methods apply to detecting microscopic defects on high-sample semiconductor wafers.
Prepare C/C++ and MATLAB Code Examples
Gather or write code snippets demonstrating proficiency in C/C++, MATLAB, and object-oriented programming on Unix/Linux platforms. Completion means you have clean, well-documented examples ready to discuss for performance-critical algorithm design.
Structure a Technical Leadership and Mentorship Walkthrough
Prepare concrete examples from past experience demonstrating how you guided engineers through complex investigative problems, set performance requirements, and supported software quality throughout the development lifecycle.
Prepare Hardware and Software Integration Scenarios
Review past projects involving system-level integration between software algorithms and hardware sub-systems. Completion means you can clearly articulate how you managed latency constraints, interface definitions, and cross-functional dependencies.
Draft Thoughtful Questions for the Interviewers
Formulate specific questions regarding the LS-SWIFT division's wafer inspection products, hardware integration workflows, and cross-functional collaboration with system and domain experts.

Availability last checked: 4 Nov 2026. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy

KEEP EXPLORING

Similar AI jobs

Related skills and specializations in India. Matched to this role, not your profile.

Explore more jobs

Finding similar opportunities…