VEDANT KUMAR
Noida
Summary
Accomplished Data Scientist with over 8 years of experience driving major projects, including India’s space telescope, ASTROSAT. Proficient in statistical analysis, machine learning, and deep learning, with a strong background in big data technologies and predictive modeling. Proven track record of contributing to innovative startups like PV Diagnostics and Altigreen Propulsion Labs, showcasing expertise in computer vision and natural language processing. Committed to leveraging advanced analytical skills to tackle complex challenges in data-driven environments.
Overview
9
9
years of professional experience
Work History
Lead Data Scientist
NRTS Services Pvt Ltd
09.2023 - Current
- Building digital transformation for profitable, safe, and sustainable oil and gas operations, predictive maintenance in upstream and midstream operations (oil and gas industry), leveraging deep learning for subsurface modeling, and early fault detection through intelligent data pipeline operations enhanced by IIoT and edge AI computing.
- Led the Generative AI framework for subsurface modeling in upstream oil and gas, enhancing data-driven decision-making with LLMs (GPT-4, BERT), and open-source NLP and RAG libraries (Hugging Face, LangChain, Pinecone, FAISS) for efficient prompt engineering.
- Automated data extraction and entity recognition, building a knowledge graph to streamline intelligent querying, and real-time insights across complex datasets (well logs, seismic data).
- Developed a multimodal RAG-based intelligent assistant, combining large vision models (CLIP, DINOv2) and vision-language models (BLIP-2, Flamingo), to perform in-depth scene understanding and contextual reasoning. It integrates text, images, and tabular data, enabling comprehensive analysis across oil and gas documents, seismic data, and well logs. This approach improved contextual data retrieval and enhanced accuracy in interpreting complex, heterogeneous datasets.
- Tech Stack: GPT-4, BERT, Hugging Face Transformers, LangChain, Pinecone, SpaCy, FAISS, Predictive AnalyticsAWS Glue, PySprak, AWS EMR, GANs, VAEs, Transformers, Vision Transformers, Diffusion models, CLIP, DINO, SAM, NIMA, BLIP, Stable Diffusion, Llama 3.2, Django, Docker, and Kubernetes.
Senior Data Scientist
Altigreen Propulsion Labs Pvt Ltd
01.2023 - 08.2023
- Contributed to integrating AI in electric vehicles (EVs) to enhance optimization, driving behavior analysis, and Advanced Driver Assistance Systems (ADAS). Led the development of Drive Score and Range Prediction, and orchestrated the development of data lakes using Spark and Snowflake.
- Implemented MLOps practices such as CI/CD, orchestration, to automate deployments, and model monitoring to ensure expected model performance in production.
- Led the development of Drive Score and Range Prediction (contributing to an enhanced user experience), and played a key role in developing vehicle diagnostics with Digital Twin and Early Fault Detection systems.
Senior Data Scientist
Kovenantz Technology Pvt Ltd
10.2021 - 12.2022
- Digital Predictive Maintenance and Digital Twin, Unsupervised Anomaly Detection on Streaming Data in the Petroleum Industry Using Deep Neural Networks. Built end to end product with DL/ML, Simulation and Optimization. DevOps, Fullstack.
Data Scientist
PV Diagnostics
10.2020 - 09.2021
- Applied Machine learning, deep learning and computer vision, and statistics to optimize power generation in large-scale solar plants. Spearheaded deep learning-based defect identification, segmentation, and object detection of solar modules through electroluminescence images, and drone thermal images. Implemented a Software as a Service (SaaS) model, providing a full-stack solution with technologies such as Docker, Nginx, Azure, AWS stack, SQL, and Spark.
Data Scientist
Sleepiz AG
03.2019 - 09.2020
- Machine learning and deep learning algorithm development, and model interpretation. Applying machine learning and deep learning modules (supervised, unsupervised, reinforcement learning) on biomedical data. Built an end-to-end pipeline, including EDA, preprocessing of data, extraction of data, feature engineering, feature selection, unsupervised learning, classification, and regression tasks.
Software Engineer
AstroSat Payload Operation Center IUCAA(ISRO)
11.2015 - 02.2019
- Analysis of astronomical data based on statistical techniques in Python and R. Development of a data software pipeline for the Astrosat mission, processing raw data acquired from the satellite into scientific products. Web application development, large-scale database development, parallel processing of data, and machine learning tools with convolutional neural networks.
Instrumentation Engineer
Avere Consulting
Chennai
06.2015 - 10.2015
- Application programming interface (API) development for drones, flight controller development, sensor integration, computer vision, crop monitoring, image analysis and segmentation, hyperspectral imaging, machine learning, Raspberry Pi, XBee, proximity sensor, GPS sensor, LIDAR
Education
Master of Science - Applied Artificial Intelligence
University of San Diego
San Diego, CA05-2026
B.Tech - ECE
Vellore Institute of Technology
Vellore01.2015
Skills
- Big Data Analysis
- Generative AI, LLMs, RAG, LVMs
- Data Science, NLP, CV
- Deep Learning Expertise
- MLOps and DevOps, Full Stack
- Cloud Computing Expertise
Publications
- Drive GPT - An AI Based Generative Driver Model, Vedant Kumar, Siddhant Jain, Nimish Soni, Amitabh Saran et al, SAE International journal, https://doi.org/10.4271/2024-26-0093
- An AI-Based Digital Twin of the Electric Vehicle (Induction Motor), Siddhant Jain, Vedant Kumar, Nimish Soni, Amitabh Saran et al, SAE International journal, https://doi.org/10.4271/2024-26-0093
- Advanced analytics on IV curves and Electroluminescence Images of Photovoltaic modules using machine learning algorithms, Vedant Kumar, Pranav Maheshwari et al, Progress in Photovoltaics: Research and Applications, https://doi.org/10.1002
- Advanced Analytics on IV Curves and Electroluminescence Images of Photovoltaic Modules Using Machine Learning Algorithms, 38th European Photovoltaic Solar Energy Conference and Exhibition
- UNIFORM MANIFOLD APPROXIMATION AND PROJECTION FOR FEATURE SELECTION ON SLEEP STAGING DATA, WORLD SLEEP 2019 CONGRESS, 09/20/19 - 09/25/19, Vancouver, Canada
- Testing Einstein-Dilaton-Gauss-Bonnet Black Hole in Strong Gravity, 29th Texas Symposium on Relativistic Astrophysics
- X-ray Spectropolarimetric Observation of Black Hole Binaries to test the General Relativity in Strong Gravity Regime, 29th Texas Symposium on Relativistic Astrophysics
- Variation of House Keeping Parameters of ASTROSAT Observatory (CZTI Instrument), 11th International Astronomical Consortium for High Energy Calibration
Schools and Conferences
- AI Summit 2024 | October 23–25, Mumbai, India | NVIDIA
- SYMPOSIUM ON INTERNATIONAL AUTOMOTIVE TECHNOLOGY SIAT 2024, Pune, India
- 38th European Photovoltaic Solar Energy Conference and Exhibition, 09/01/21, Munich, Germany
- WORLD SLEEP 2019 CONGRESS, 09/20/19 - 09/25/19, Vancouver, Canada
- 11th International Astronomical Consortium for High Energy Calibration, 03/01/16, IUCAA, Pune, India
- Introductory Summer School of Astronomy and Astrophysics, 06/01/17, IUCAA, Pune, India
- American Astronautical Society's CanSat Competition, 08/01/15, Burkett, Texas, USA
- Texas Instrumentation Innovation Challenge India Design Contest, 01/01/15, Bangalore, India
Technologies
TensorFlow, Keras, PyTorch, scikit-learn, MXNet, FastAI, NLTK, Hugging Face, LangChain, LlamaIndex, Pinecone, GateNLP, Chroma, Haystack, FAISS, OpenAI API, timm, MM Detection, Torchvision, Detectron2, MLflow, Kubeflow, TFX, Metaflow, TensorRT, Docker, Kubernetes, OpenShift, Jenkins, GitLab CI, GitHub Actions, CircleCI, Travis CI, AWS, Azure, Google Cloud, Snowflake, Databricks, Python, Scala, Java, C, C++, R, MATLAB, Bash, Shell Scripting, Python (Pandas, NumPy, SciPy), multiprocessing, Apache Spark, Apache Kafka, Apache Hadoop, Apache Flink, Airflow, MongoDB, Hadoop, MySQL, PySpark, Neo4j, NumPy, SciPy, BioSPPy, Pandas, Dask, XGBoost, pymc3, Numba, Arrow, PowerBI, Tableau, Matplotlib, Seaborn, Bokeh, Plotly, Prometheus, Grafana, New Relic, ELK Stack, Splunk, Unix, Linux, CUDA, CuDNN, MPI, OpenMPI
Timeline
Lead Data Scientist
NRTS Services Pvt Ltd
09.2023 - Current
Senior Data Scientist
Altigreen Propulsion Labs Pvt Ltd
01.2023 - 08.2023
Senior Data Scientist
Kovenantz Technology Pvt Ltd
10.2021 - 12.2022
Data Scientist
PV Diagnostics
10.2020 - 09.2021
Data Scientist
Sleepiz AG
03.2019 - 09.2020
Software Engineer
AstroSat Payload Operation Center IUCAA(ISRO)
11.2015 - 02.2019
Instrumentation Engineer
Avere Consulting
06.2015 - 10.2015
Master of Science - Applied Artificial Intelligence
University of San Diego
B.Tech - ECE
Vellore Institute of Technology
Similar Profiles
SNEHA SSNEHA S
HR Recruiting Associate at Accenture Services Pvt Ltd- On rolls of V5 Global Services Pvt Ltd. 04th Sep 2023 to till dateHR Recruiting Associate at Accenture Services Pvt Ltd- On rolls of V5 Global Services Pvt Ltd. 04th Sep 2023 to till date
Swathika V VSwathika V V
Senior Analyst I Data Engineering at DXC Technology ( EIT Services India Pvt., Ltd., formerly known as HP Global Soft Pvt., Ltd, ChennaiSenior Analyst I Data Engineering at DXC Technology ( EIT Services India Pvt., Ltd., formerly known as HP Global Soft Pvt., Ltd, Chennai
Savithri IyerSavithri Iyer
Data Analyst at Manpower Group Services, FedEx Express Transportation and Supply Chain Services (India) Pvt. LtdData Analyst at Manpower Group Services, FedEx Express Transportation and Supply Chain Services (India) Pvt. Ltd