Hi, I’m Sai Prasanna, a Generative AI Engineer with around 10 years of experience delivering LLM- and diffusion-based solutions across NLP, computer vision, and multi-modal AI applications. I excel at translating complex business problems into scalable AI systems, from data preprocessing to deployment, payback analytics, and governance in regulated environments. I specialize in retrieval-augmented generation, prompt engineering, and vector databases, and I enjoy collaborating with cross-functional teams to embed AI into enterprise platforms (e.g., claims, underwriting, document intelligence) while upholding Responsible AI principles and guardrails. I’m hands-on with cutting-edge models (GPT-4, LLaMA, Claude) and cloud-native MLOps across AWS, GCP, and Azure.

Sai Prasanna

Hi, I’m Sai Prasanna, a Generative AI Engineer with around 10 years of experience delivering LLM- and diffusion-based solutions across NLP, computer vision, and multi-modal AI applications. I excel at translating complex business problems into scalable AI systems, from data preprocessing to deployment, payback analytics, and governance in regulated environments. I specialize in retrieval-augmented generation, prompt engineering, and vector databases, and I enjoy collaborating with cross-functional teams to embed AI into enterprise platforms (e.g., claims, underwriting, document intelligence) while upholding Responsible AI principles and guardrails. I’m hands-on with cutting-edge models (GPT-4, LLaMA, Claude) and cloud-native MLOps across AWS, GCP, and Azure.

Available to hire

Hi, I’m Sai Prasanna, a Generative AI Engineer with around 10 years of experience delivering LLM- and diffusion-based solutions across NLP, computer vision, and multi-modal AI applications. I excel at translating complex business problems into scalable AI systems, from data preprocessing to deployment, payback analytics, and governance in regulated environments.

I specialize in retrieval-augmented generation, prompt engineering, and vector databases, and I enjoy collaborating with cross-functional teams to embed AI into enterprise platforms (e.g., claims, underwriting, document intelligence) while upholding Responsible AI principles and guardrails. I’m hands-on with cutting-edge models (GPT-4, LLaMA, Claude) and cloud-native MLOps across AWS, GCP, and Azure.

See more

Language

English
Fluent

Work Experience

Gen AI Engineer at Molina Health Care
August 1, 2024 - Present
Led development and deployment of large language model-powered applications, including RAG systems, summarization, Q&A, and multimodal AI tools using OpenAI, LangChain, and fine-tuned models. Built and deployed APIs and pipelines using Stable Diffusion, CLIP, Whisper, and vector databases for marketing automation and customer support. Employed prompt engineering to reduce hallucinations, integrated monitoring tools for performance tracking, and collaborated cross-functionally to embed generative AI features. Contributed to open source projects, conducted model evaluations, and authored internal white papers on AI ethics and safety.
Gen AI / Data Scientist at Edward Jones
July 31, 2024 - August 5, 2025
Developed few-shot and zero-shot classification systems and reusable prompt libraries, integrating vector databases with LangChain for semantic search at scale. Deployed containerized LLM inference with GPU autoscaling on cloud platforms and built observability dashboards. Combined multimodal AI such as Whisper ASR and GPT-4 for real-time summarization. Led ethical AI implementations including toxicity and bias detection, taught internal AI workshops, led cross-functional initiatives, and applied parameter-efficient fine-tuning techniques for foundation models.
Machine Learning Engineer at Bank of America
September 30, 2022 - August 5, 2025
Built custom transfer learning models and deep learning pipelines to process terabyte-scale datasets. Automated real-time data ingestion, implemented model evaluation, monitoring, and deployment on cloud infrastructure serving millions of predictions. Delivered predictive analytics producing significant cost savings, managed A/B testing frameworks, developed and deployed deep learning models for NLP and vision tasks, built data ingestion pipelines, and applied model explainability techniques. Led cross-functional collaborations and mentored junior engineers on ML best practices.
Data Scientist at Oracle
June 30, 2020 - August 5, 2025
Conducted exploratory data analysis, feature engineering, and built ML models for customer churn reduction and marketing mix optimizations using Scikit-learn and TensorFlow. Led clustering and NLP analysis on customer feedback, managed big data solutions on Hadoop and Spark, and maintained detailed documentation for model lifecycle. Established CI/CD workflows and mentored junior data scientists while improving data quality and AI/ML model scalability by integrating various databases and vector search technologies.
Python Developer at HCL Technologies
October 31, 2017 - August 5, 2025
Developed dashboards and visual reports, fine-tuned deep learning models for image and text classification, applied NLP techniques, integrated pretrained transformer models, and monitored model drift. Collaborated with engineering teams to implement CI/CD pipelines for scalable ML deployments. Executed hyperparameter tuning and dimensionality reduction to optimize models and aligned developments with product roadmaps. Implemented MLOps workflows to maintain fraud detection and recommender engines, ensuring accurate and scalable AI solutions.
Gen AI / Data Scientist at Edward Jones
October 1, 2022 - July 1, 2024
Built few-shot and zero-shot classification using GPT-4, Claude, and Cohere Command R+; developed prompt evaluation framework using LLM-as-judge; created internal libraries and tooling for scalable deployment across units. Integrated vector databases (Weaviate, Pinecone) with LangChain to support semantic search over millions of documents. Deployed containerized LLM inference stacks on AWS SageMaker and GCP Vertex AI; built observability dashboards to monitor token usage, latency, hallucination rate, and cost with Weights & Biases and Prometheus. Combined Whisper ASR with GPT-4 for real-time multilingual meeting summarization and speaker attribution. Built CLIP-powered recommendations; evaluated OpenAI, Anthropic, and Cohere APIs. Maintained CI/CD pipelines and developed evaluation frameworks with BLEU/ROUGE and human-in-the-loop. Developed toxicity and bias filters and designed a GenAI-powered contract parsing assistant (RAG+LLM). Led internal bootcamps and cross-functional collaborat
Machine Learning Engineer at Bank of America
July 1, 2020 - September 1, 2022
Built scalable ML pipelines using TensorFlow and PyTorch on terabyte-scale data; deployed real-time models via Docker, Kubernetes, and AWS SageMaker. Automated data ingestion from Kafka and REST APIs; designed robust evaluation (AUC-ROC, precision-recall) and monitoring (MLflow, Prometheus). Implemented CI/CD and model versioning; built end-to-end ML workflows with Apache Airflow. Achieved business impact with predictive analytics, saving around $1.5M annually. Implemented model explainability (SHAP/LIME) and drift detection; supported fraud analytics and risk modeling. Collaborated with cross-functional teams in an Agile environment; produced reusable ML components and dashboards for stakeholders.
Data Scientist at Oracle
February 1, 2018 - June 1, 2020
Led EDA and feature engineering for churn prediction and customer segmentation; built marketing mix models; performed data extraction and cleaning from Cassandra, PostgreSQL, and MySQL. Implemented vector DB integration for high-dimensional data; deployed containerized inference on AWS/GCP; used Grid Search and 10-fold cross-validation. Built NLP on customer feedback and clustering; developed Databricks pipelines; set up Jenkins CI/CD; ensured model explainability and governance. Mentored juniors; led knowledge-sharing sessions; established data aggregation pipelines and feature engineering.
Python Developer at HCL Technologies
September 1, 2015 - October 1, 2017
Created dashboards with Tableau and Power BI; built and fine-tuned deep learning models using TensorFlow and PyTorch; applied NLP techniques (sentiment analysis, NER, topic modeling) to extract insights from unstructured text. Integrated pretrained transformers for document classification and semantic similarity. Monitored model drift and retrained; collaborated with DevOps for scalable ML deployments; established CI/CD; mentored juniors and led knowledge sharing.
Gen AI Engineer at Edward Jones
October 1, 2022 - July 31, 2024
Led end-to-end GenAI initiatives including few-shot/zero-shot classification, LLM evaluation via LLM-as-a-judge, and human-in-the-loop; implemented vector databases (Weaviate, Pinecone) with LangChain for semantic search; built RAG pipelines and multi-LLM orchestration; containerized inference on AWS SageMaker and GCP Vertex AI; ensured privacy/compliance with PII.
Senior Data Scientist at Oracle
February 1, 2018 - June 1, 2020
Led customer analytics including churn factor analysis, segmentation, and marketing mix modeling; applied NLP to customer feedback; built data pipelines; established model governance and documentation; collaborated with cross-functional teams.
Data Scientist at HCL Technologies
September 1, 2015 - October 1, 2017
Created dashboards and built deep learning models for image/text tasks; applied NLP, transformer-based document classification and semantic similarity; implemented CI/CD pipelines; mentored juniors; built end-to-end ML lifecycle and data preprocessing pipelines.

Education

Add your educational history here.

Qualifications

Add your qualifications or awards here.

Industry Experience

Healthcare, Financial Services, Software & Internet, Professional Services