ABHISHEK GOYAL

AI Researcher

Bengaluru, Karnataka, India8 yrs 6 mos experience

Most Likely To SwitchAI Enabled

Key Highlights

Expert in multimodal image understanding and computer vision.
Developed innovative generative AI solutions for language translation.
Significantly improved defect detection accuracy in semiconductor imaging.

Stackforce AI infers this person is a skilled professional in AI and computer vision for high-tech and automotive industries.

Contact

Skills

Core Skills

Computer VisionDeep LearningGenerative AiProblem SolvingData ScienceMachine Learning

Other Skills

AgentsCC (Programming Language)C++CADClustering AlgorithmsData AnalysisData AnalyticsData PreprocessingData VisualizationDefect DetectionDockerEDAEngineeringGANs

About

Passionate about advancing AI research and translating it into impactful applications. My work focuses on multimodal image understanding, domain translation, and building intelligent systems that bridge complex data modalities.I thrive at the intersection of deep learning, computer vision, and generative AI, turning cutting-edge ideas into solutions that drive innovation in high-tech industries.

Experience

Applied materials

2 roles

Technical Lead - Computer vision (R&D, Optical Water Defect Inspection Team)

Promoted

Dec 2024 – Present · 1 yr 3 mos · Bengaluru, Karnataka, India · Hybrid

Multimodal Image Registration: Built a deep learning pipeline for accurate registration between optical scan images and CAD data, enabling pixel-level alignment during recipe setup. This innovation led to rigid die alignment and leveraged CAD information to significantly improve defect sensitivity.
Agentic AI for Algorithm Development: Developed an autonomous agent using GPT-4, Streamlit and Phi data to convert natural language queries into executable Python workflows with interactive visualization.

Multimodal Image RegistrationDeep LearningComputer VisionPythonCAD

Algorithm Developer - Computer vision (R&D, Optical Water Defect Inspection Team)

Jun 2022 – Oct 2024 · 2 yrs 4 mos · Bangalore Urban, Karnataka, India · Hybrid

Develop Deep Learning pipeline using PyTorch framework.
Developing and experimenting with Deep Learning based defect detection algorithms to detect defects in
low resolution (266 nm) images of semiconductor wafers. Analyzing dataset to develop a defect planting
strategy to extend the dataset size.
Reduced the computation requirement of the model by developing Half UNet architecture that requires 90%
less computation and 90% less parameters for defect detection task compared to UNet.
Improved the detection accuracy of existing algorithm by 30% along with improving throughput to 3 times
by providing output for three images at a time.
Awards:
Awarded first place in a Hackathon with over 80 teams for developing a unique Generative AI solution. Our innovative approach translates videos from Ivrit to English while preserving the original speaker's voice attributes. This has made crucial technical lectures accessible in both Ivrit/Hebrew and English, bridging language barriers in the tech community.

Deep LearningPyTorchDefect DetectionData AnalysisData Science

Mobis technical center of india(hyundai mobis r &d)

Senior Research Engineer (R&D: Camera Team)

Nov 2020 – May 2022 · 1 yr 6 mos · Hyderabad, Telangana, India

Experimenting with GANs to develop models for creating synthetic datasets to be used in training of Image translation and object detection algorithms.
Developing and implementing GAN based algorithms for image
domain translation - transforming output of gaming engine to
photo-realistic images.
Developing and improving results for semantic segmentation using
Deep Learning architectures like UNET on limited dataset.
Using self-supervised techniques to learn better visual representation
of the images and transfering the learned weights for
improving the performance of the UNET model.

GANsImage TranslationSemantic SegmentationDeep LearningComputer Vision

Continental

Machine Learning Intern

Jan 2020 – Nov 2020 · 10 mos · India

I am working on Stationary vehicle classification using Radar Data.
The task involved:
Developing Algorithm to obtain data for vehicle from the radar data consisting of data related to
moving objects, stationary objects such as (vehicles, pedestrian, gantry sign, bridges, guard rail, etc.).
This includes trying various clustering algorithms (such as DBSCAN, K-Means, etc.) and various
distance metric such as Euclidean distance and Mahalanobis distance.
Performing Exploratory Data Analysis to identify features of interest and identifying patterns in the
data enabling us to decide which model would perform better with the data in hand.
Data Preprocessing to balance the imbalance dataset.
Applying machine learning classification algorithms (Logistic Regression, SVM, KNN, Neural Network and LSTM) and comparing there performance for classifying truck and car objects.