Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am a data scientist with 3+ years building end-to-end machine learning systems for computer vision, generative AI, and distributed model training. I design and optimize deep learning models, implement scalable inference pipelines, and deploy high-performance ML workflows. I have a strong foundation in statistics, deep learning, and generative modeling, with practical MLOps experience across versioning, automation, API development, and cost-efficient deployment.…I am a data scientist with 3+ years building end-to-end machine learning systems for computer vision, generative AI, and distributed model training. I design and optimize deep learning models, implement scalable inference pipelines, and deploy high-performance ML workflows. I have a strong foundation in statistics, deep learning, and generative modeling, with practical MLOps experience across versioning, automation, API development, and cost-efficient deployment.

Srivatsava Kasibhatla

Data Scientist, AI Engineer, Full Stack Developer, +2





I am a data scientist with 3+ years building end-to-end machine learning systems for computer vision, generative AI, and distributed model training. I design and optimize deep learning models, implement scalable inference pipelines, and deploy high-performance ML workflows. I have a strong foundation in statistics, deep learning, and generative modeling, with practical MLOps experience across versioning, automation, API development, and cost-efficient deployment.…I am a data scientist with 3+ years building end-to-end machine learning systems for computer vision, generative AI, and distributed model training. I design and optimize deep learning models, implement scalable inference pipelines, and deploy high-performance ML workflows. I have a strong foundation in statistics, deep learning, and generative modeling, with practical MLOps experience across versioning, automation, API development, and cost-efficient deployment.

Available to hire

I am a data scientist with 3+ years building end-to-end machine learning systems for computer vision, generative AI, and distributed model training. I design and optimize deep learning models, implement scalable inference pipelines, and deploy high-performance ML workflows.

I have a strong foundation in statistics, deep learning, and generative modeling, with practical MLOps experience across versioning, automation, API development, and cost-efficient deployment.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Work Experience

Data Scientist at Viridien (formerly CGG)

July 1, 2022 - November 26, 2025

Led development of ML solutions processing satellite data for global scale pollution monitoring, image enhancement, automating manual workflows and improving product sales through effective communication. Designed and deployed an oil pollution detection model based on Vision Transformers using PyTorch and MLflow, reducing manual review by 64% and generating over 1M USD in annual value. Optimized inference through model quantization, ONNX Runtime and Triton Server with graph and batching optimizations, enabling real time processing of gigabyte scale imagery with a 31% latency reduction. Created ETL pipelines and clustering workflows using pandas, NumPy and scikit-learn with Airflow orchestration, discovering 3 new pollution sources and contributing to acquisition of 2 new clients. Developed a satellite image resolution enhancement model using Diffusion and CNN architectures and deployed it via FastAPI with SLURM based batch processing, increasing quarterly image sales by 8%. Built a min

Machine Learning Intern at Wadhwani AI

July 1, 2021 - July 1, 2021

Automated pest detection and counting from crop images by training YOLOv5 models with multi GPU and Hydra pipelines, achieving 89% count accuracy and a 12% improvement on small pests. Deployed optimized models to farmer mobile devices using TorchScript and TensorFlow Lite to enable real time scanning and multilingual pesticide recommendations across 7 languages and 5 crop types.