Tejaswini Pasam

About Tejaswini Pasam

I’ve always believed that data isn’t just numbers—it’s potential. Potential to drive change, unlock opportunities, and solve real-world problems. With over 5 years of experience as an AI & Machine Learning Engineer, I’ve had the privilege of working across healthcare, finance, and e-commerce to build intelligent systems that deliver measurable impact.Currently, I’m focused on integrating the power of Generative AI and large language models (LLMs) into production environments. At HSBC, I work with technologies like GPT-4, LangChain, FAISS, and Pinecone to create smart, scalable solutions—whether it\'s building Retrieval-Augmented Generation (RAG) systems, deploying chatbots, or automating document intelligence.I enjoy combining deep technical expertise with practical application—automating data pipelines, deploying models on AWS SageMaker and Google Vertex AI, and integrating responsible AI practices like explainability and fairness. Whether it’s streamlining workflows with Python and SQL or visualizing impact with Power BI and Tableau, I’m passionate about turning complex ideas into simple, actionable solutions.Beyond the technical side, I genuinely enjoy collaborating with cross-functional teams, sharing knowledge, and staying curious. I’m always learning—whether it\'s through certifications, reading research papers, or connecting with fellow tech enthusiasts. I’m open to opportunities in:Generative AI & NLPHealthcare and Financial AI ApplicationsCloud-based AI/MLOps EngineeringData & ML Pipeline AutomationAI Innovation Teams and R & DIf you\'re working on something exciting in the AI/ML space or looking for someone who can bridge the gap between data, models, and impact—I’d love to connect.

Experience

1. Gen Ai Developer

   HSBC

   Apr 2024 — Present · Dallas, TX, US

   Designed and deployed advanced Generative AI solutions using GPT-3, GPT-4, and BERT for tasks like content creation, summarization, and conversational AI across diverse applications-Built and integrated AI-driven applications using LangChain and LangGraph-style orchestration frameworks, orchestrating multi-step agent workflows involving large language models for question answering, document processing, and intelligent automation-Developed Retrieval-Augmented Generation (RAG) systems by combining LLMs with vector databases such as FAISS and Pinecone to retrieve relevant context and generate factually accurate outputs-Engineered and optimized prompts for OpenAI APIs to fine-tune LLM responses for domain-specific tasks such as customer service automation and personalized content generation-Deployed large-scale LLMs on AWS SageMaker and Google Vertex AI, ensuring high availability, scalability, and performance of models in production environments-Integrated generative AI models with external APIs and enterprise systems to deliver domain-specific solutions across industries including healthcare, e-commerce, and finance-Built real-time, intelligent chatbots using GPT-3 integration, delivering context-aware conversational experiences for customer-facing platforms-Built interactive AI agent demos using Streamlit and similar Python-based UI frameworks to showcase LangChain/Vertex AI capabilities to stakeholders-Created and maintained CI/CD pipelines using Jenkins, Docker, and Kubernetes for seamless model deployment, versioning, and operational monitoring-Developed computer vision algorithms for object detection using OpenCV, Keras, and TensorFlow, extending AI capabilities beyond text into image-based workflows-Ensured responsible AI practices by incorporating explainability (SHAP), fairness, and compliance while collaborating with data scientists, engineers, and business stakeholders to deliver impactful AI solutions.

Education

• The University of Texas at Arlington

  Master's degree

  2022 — 2024