Skip to content
View prithviraj-maurya's full-sized avatar

Highlights

  • Pro

Block or report prithviraj-maurya

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
prithviraj-maurya/README.md

πŸ‘‹ Hi, I'm Prithviraj Maurya

Senior Machine Learning Engineer | Ex-Amazon | Ex-Morgan Stanley | Data Scientist | Generative AI Enthusiast

πŸ” Passionate about crafting robust AI/ML systems, building scalable data infrastructure, and delivering business-impacting insights through cutting-edge machine learning solutions.


πŸ’Ό Experience

πŸ“¦ Software Engineer - AI/ML

Amazon (Social Ads Team) | May 2023 – Aug 2023

  • Built and deployed a Content Quality Evaluation System to automatically assess and flag poor-quality influencer content (videos/images).
  • Used Amazon Bedrock, LLMs, and custom scoring metrics to evaluate content fitness for advertising.
  • Took the project from scratch to production, reducing low-quality content by 30%+ and improving engagement and conversion.
  • Developed scalable dashboards for content performance tracking and insights.

🧠 Senior Machine Learning Engineer

Thomson Reuters | Aug 2023 – Sep 2024

  • Led the development of a domain-specific Legal Language Model (LLM) for legal NLP tasks.
  • Built end-to-end MLOps pipelines for model training, evaluation, and deployment.
  • Collaborated cross-functionally with legal experts and ML researchers to align models with real-world legal use cases.
  • Delivered optimization improvements that significantly accelerated legal document classification tasks.

πŸ§‘β€πŸ’» Senior Software Engineer

Morgan Stanley | Aug 2020 – Jul 2022

  • Designed and developed real-time financial dashboards and hybrid apps for asset managers.
  • Architected performant backend services, improving latency and UI responsiveness by 40%.
  • Integrated analytics and forecasting tools to aid in portfolio decision-making.

πŸŽ“ Education

M.S. in Data Science
Indiana University Bloomington | Aug 2022 – May 2024


🧰 Skills

  • Languages: Python, SQL, JavaScript
  • ML/AI: PyTorch, TensorFlow, Scikit-learn, HuggingFace, LLMs, LangChain, VLLMs
  • Data Engineering: Apache Spark, Airflow, Pandas, AWS (S3, Lambda, Bedrock)
  • DevOps/MLOps: Docker, MLflow, SageMaker, GitHub Actions, CI/CD
  • Cloud: AWS, Azure, GCP
  • Others: Tableau, Power BI, REST APIs, Streamlit

πŸ† Achievements

  • πŸš€ Boosted product recommendation conversions by 30%+ during internship at Amazon.
  • πŸ“„ Published research on voice assistant NLP models.
  • πŸ” AWS Certified Developer – Associate
  • πŸ§ͺ Kaggle Expert
  • πŸ“š Contributor to PyTorch documentation (Docathon)

πŸ“« Let's Connect


⭐️ Fun Fact: I love simplifying complex problems with elegant ML solutions β€” always up for building the next big thing in AI!

Pinned Loading

  1. alexa-point-of-view-dataset alexa-point-of-view-dataset Public

    Forked from alexa/alexa-point-of-view-dataset

    Point of View (POV) conversion dataset. Messages spoken to virtual assistants are converted from sender perspective to virtual assistant's perspective for delivery.

    Jupyter Notebook

  2. legalbench_legal_llm legalbench_legal_llm Public

    This project is intended to provide a summary of the task involving exploring the LegalBench dataset, understanding its structure, and evaluating various approaches, including text classification, …

    HTML 1

  3. detect_llm_generated_essay detect_llm_generated_essay Public

    How can machine learning techniques be effectively employed to identify essays generated by large language models (LLMs) compared to those authored by middle and high school students?

    Jupyter Notebook 1 1

  4. mapreduce-based-machine-learning mapreduce-based-machine-learning Public

    Large-scale Artificial Neural Network: MapReduce-based for Machine Learning

    Python 2

  5. TayorSwift_Eras_Tour-Dash TayorSwift_Eras_Tour-Dash Public

    Fifty-two dates, 20 stadiums, 10 albums, 44 songs taking up more than three hours: Taylor Swift’s Eras Tour, which kicked off March 17 at State Farm Arena in Glendale, Arizona, is a production of e…

    Python 1