Poornima S

Generative Text Models for Creative Writing

• Description: Developed a generative model to assist in creative writing, producing poems, stories, and marketing copy.
• Technologies Used: Python, GPT-3/GPT-4 (OpenAI), Hugging Face Transformers, TensorFlow, PyTorch.
• Skills Demonstrated: Deep learning, NLP, model fine-tuning, prompt engineering, creative applications of AI.
• Key Achievements:Fine-tuned a GPT-3 model to generate contextually appropriate creative content.
  Implemented a web interface for users to interact with the generative model.
  

Chatbot with Emotional Intelligence

• Description: Built an advanced chatbot capable of understanding and responding to user emotions using sentiment analysis and empathetic dialogue generation.
• Technologies Used: Python, Rasa, TensorFlow, Hugging Face Transformers, NLTK, SpaCy.
• Skills Demonstrated: Conversational AI, sentiment analysis, NLP, deep learning, user interaction design.
• Key Achievements:Designed and trained sentiment analysis models to detect user emotions in real-time.
  Developed a dialogue management system to generate empathetic responses.
  

Document Summarization and Insights Extraction

• Description: Created a system to automatically summarize large documents and extract key insights, useful for legal, medical, or financial documents.
• Technologies Used: Python, BERT, GPT, Hugging Face Transformers, NLTK, SpaCy.
• Skills Demonstrated: NLP, text summarization, information extraction, deep learning.
• Key Achievements:Implemented BERT-based models for accurate document summarization.
  Extracted actionable insights from complex documents, reducing analysis time by 60%.
  

AI-Powered Resume Screening Tool

• Description: Developed an AI tool to screen and rank resumes based on job descriptions, highlighting key skills and experiences that match the requirements.
• Technologies Used: Python, BERT, SpaCy, Scikit-learn, Flask.
• Skills Demonstrated: NLP, information retrieval, machine learning, web development.
• Key Achievements:Achieved 85% accuracy in matching resumes to job descriptions.
  Built an interactive web interface for HR professionals to use the tool.
  

• Coordinated with other professionals involved in the mentoring process to ensure seamless support for each participant''s journey toward success.
• Developed rapport with mentees'' supervisors, enabling a collaborative approach to supporting mentee growth and development within their workplace context.
• Adapted mentorship style based on individual mentee needs, enabling tailored interventions that drove better results than one-size-fits-all approaches.
• Evaluated program success through regular assessments of participant satisfaction, engagement levels, and achievement rates.

Data Science Intern Jun 2022 – Feb 2024

Sentiment Analysis on Social Media Data:

• Build a predictive model to identify customers likely to churn from a subscription service.
• Tools used Python, Pandas, Matplotlib, SQL
• Data cleaning, exploratory data analysis (EDA), feature engineering, machine learning model development, evaluation metrics
• Sentiment Analysis on Social Media Data: Analyze the sentiment of tweets or product reviews to understand public opinion about a brand or product.
  Tools used Python
  Natural Language Processing (NLP), text data preprocessing, sentiment analysis, data visualization.

● Built Tableau dashboard to visualize core business KPIs (e.g. Monthly Recurring Revenue), saving 10 hours per week of manual reporting work

● Aggregated unstructured data from 20+ sources to build the foundation of a new product; led to $100,000 in new revenue

● Designed the data pipeline architecture in team of 5 for a new product that scaled from 0 to 100,000 daily active users

• Providing support & troubleshoot for clients using Azure AD Identity workloads
• Supporting Technologies including Azure AD, Administrative Unit, Identity Management, PIM, Single Sign On(SSO), ADFS, Azure AD Connect
• Cross support for customers using other Azure services; Azure Virtual Networks, Virtual Machines & advisory on Customer Billings & Subscription
• Experience in Syncing the Objects Users, Groups, Workstation from active directory to azure active directory
• Managed Azure identity and access (IAM) with a focus on least privilege access for both Azure subscriptions and Azure AD.

• Resolve incident in time as expected by the user and handle escalation break fix and change requests
• Generate daily call report to the Global desk management
• Software installation & troubleshooting (Application Support)
• Provide Admin rights, enabling/disabling Hostname
• User access management creation/deletion/modification on Windows AD
• Checking and help improving the system infrastructure performance
• Log check, monitoring, security and reporting.