• Leading and managing AI/ML initiatives, focusing primarily on Generative AI. Driving the development and implementation of innovative AI/ML solutions, leveraging generative AI techniques to deliver cutting-edge products and services.
• Fostering a collaborative and inclusive work environment, promoting teamwork and synergy among team members to maximize productivity and achieve project goals.
• Providing expert consultation and guidance to clients, leveraging my deep understanding of AI/ML technologies and industry best practices. Actively contribute to the AI community through knowledge sharing, presenting at conferences, and participating in industry events.

• Lead the development of end-to-end machine learning solutions and services at Elsevier, employing state-of-the-art deep learning models, LLMs with LangChain, and AWS platform services such as Sagemaker.
• Collaborate closely with colleagues to define project scope, establish objectives and deliverables, and manage projects using JIRA, employing both KANBAN and Scrum methodologies.
• Demonstrated strong project management skills, overseeing tasks such as data creation, model development, testing, and deployment.
• Maintained clear and concise documentation throughout the project, facilitating knowledge transfer and ensuring effective collaboration among team members.
• Consistently met project deadlines and delivered high-quality results, contributing to the overall success of the team and organization.

• Following is one of my recent projects -

  • LLM and BERT-based Automatic Scientific Article Publishing Pipeline:  Utilized LayoutLM Document AI and GPT One-shot Prompts with Langchain to enhance the efficiency and accuracy of the publishing process. Reducing `Paper Post Editing` time by employing ML-based Automations. 

• Involved in the development and implementation of automatic document structuring and comprehension techniques, utilizing deep learning models to extract knowledge from lengthy unstructured contexts.  Where, I successfully applied Bi-LSTM+CRFs, BERTs, Longformers, and LayoutLMs to extract entities such as titles, authors, sections, references, and drug names from research articles, improving the efficiency and accuracy of our information retrieval engine.
• Developed confidence calibrators for deep learning models, enhancing their reliability and interpretability in real-world applications.
• Led the identification and structuring of references in scientific documents, streamlining the citation process and facilitating easier access to relevant research.
• Utilized LSTM+CRFs to extract biomedical entities from scientific articles, contributing to advancements in the field of biomedical research and knowledge discovery.
• Following are some of my successful initiatives:
  • Scientific Document Structuring and Analysis
  • Extraction of Entities (Title, Author, Scetions, Reference, Drug Name etc) from Research Articles) using Bi-LSTM+CRFs, BERTs, Longformers, LayoutLMs
  • Confidence Calibrators for deep-learning models
  • Reference Identification and Structuring in Scientific Documents
  • Extraction of Biomedical Entities from Scientific Articles using LSTMs and CRFs

• Collaborated with Accenture Labs and University College Dublin on a joint research project aimed at developing automated Anti-Money Laundering Solutions using NLP and deep learning techniques.
• Applied NLP, NER, Relation Extraction and Knowledge Graphs to enhance the accuracy of AML investigations, reducing human effort and increasing detection rates.
• Developed a knowledge graph specific to the finance domain, leveraging neural networks and TensorFlow to improve the performance of the automated AML system.
• Utilized Python and Git for code development and version control, ensuring efficient and organized project management.
• Presented system demos at conferences, effectively communicating the capabilities and potential impact of the research to industry professionals and stakeholders.
  • Published a paper titled "NextGen AML: Distributed Deep Learning based Language Technologies to Augment Anti Money Laundering Investigation" at ACL 2018, showcasing the advancements made in the field.

• Developed a decentralized system for NLP and Machine Learning modules, gathering information and intelligence for economic organizations (banks/insurance) to assess the risk and threat associated with clients.
• Applied NLP, NER, Relation Extraction, Aspect-based Sentiment Analysis, and Knowledge Graph techniques to extract relevant information from financial data and identify entities involved in scams, frauds, and money laundering.
• Utilized expertise in the finance domain, including KYC and Panama Papers, to enhance the accuracy and effectiveness of clients Anti Money Laundring System.
• Implemented Neural Nets and Tensorflow for training and deploying machine learning models, achieving high performance and accuracy.  Leveraged Neo4j and RabbitMQ for data storage and message queuing, optimizing system performance and scalability.
• Collaborated with a team of researchers and engineers across Universities and Accenture lab, Dublin.
  • Developed and filed a patent for an Integrated monitoring and communications system using a knowledge graph-based explanatory equipment management approach.

• Led the development of a multilingual search engine on the tourism domain, based on Apache Lucene, as part of the Cross Lingual Information Access System (Sandhan Phase - II) project at Jadavpur University.
• Responsible for generating automatic query-focused summaries and snippets for web pages, developing a query expansion module, and implementing textual entailment-based ranking algorithms.
• Successfully implemented Java and J2EE technologies, along with Apache Lucene and Nutch, to create a robust and efficient search engine.

Publications(s):

•  Pakray, P., Barman, U., Bandyopadhyay, S. and Gelbukh, A., 2012. Semantic answer validation using universal networking language. International Journal of Computer Science and Information Technologies, 3(4), pp.4927-4932.
•  Pakray, P., Barman, U., Bandyopadhyay, S. and Gelbukh, A., 2011. A statistics-based semantic textual entailment system. Advances in Artificial Intelligence, pp.267-276.