Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I’m Lalitharani Palakaluri, a Senior AI/ML Engineer focused on building end-to-end AI systems, data pipelines, and GenAI solutions that ground large language models in enterprise data. I’ve led initiatives across data engineering, applied ML, GenAI, RAG, and Agentic AI platforms, delivering production-grade solutions on AWS, Azure, and GCP. I’m passionate about engineering-first AI—prioritizing reliability, scalability, governance, and cost efficiency while collaborating with cross-functional teams to translate real-world workflows into scalable automation. Beyond modeling, I enjoy designing robust architectures, optimizing inference cost, and building secure, observable AI services that drive measurable business impact. I love mentoring teams, promoting best practices in MLOps, and continuously iterating on prompts, context management, and tool use to deliver grounded, safe, and helpful AI experiences.…Hi, I’m Lalitharani Palakaluri, a Senior AI/ML Engineer focused on building end-to-end AI systems, data pipelines, and GenAI solutions that ground large language models in enterprise data. I’ve led initiatives across data engineering, applied ML, GenAI, RAG, and Agentic AI platforms, delivering production-grade solutions on AWS, Azure, and GCP. I’m passionate about engineering-first AI—prioritizing reliability, scalability, governance, and cost efficiency while collaborating with cross-functional teams to translate real-world workflows into scalable automation. Beyond modeling, I enjoy designing robust architectures, optimizing inference cost, and building secure, observable AI services that drive measurable business impact. I love mentoring teams, promoting best practices in MLOps, and continuously iterating on prompts, context management, and tool use to deliver grounded, safe, and helpful AI experiences.

Lalitharani Palakaluri

AI Engineer, Data Scientist, Full Stack Developer, +2





Hi, I’m Lalitharani Palakaluri, a Senior AI/ML Engineer focused on building end-to-end AI systems, data pipelines, and GenAI solutions that ground large language models in enterprise data. I’ve led initiatives across data engineering, applied ML, GenAI, RAG, and Agentic AI platforms, delivering production-grade solutions on AWS, Azure, and GCP. I’m passionate about engineering-first AI—prioritizing reliability, scalability, governance, and cost efficiency while collaborating with cross-functional teams to translate real-world workflows into scalable automation. Beyond modeling, I enjoy designing robust architectures, optimizing inference cost, and building secure, observable AI services that drive measurable business impact. I love mentoring teams, promoting best practices in MLOps, and continuously iterating on prompts, context management, and tool use to deliver grounded, safe, and helpful AI experiences.…Hi, I’m Lalitharani Palakaluri, a Senior AI/ML Engineer focused on building end-to-end AI systems, data pipelines, and GenAI solutions that ground large language models in enterprise data. I’ve led initiatives across data engineering, applied ML, GenAI, RAG, and Agentic AI platforms, delivering production-grade solutions on AWS, Azure, and GCP. I’m passionate about engineering-first AI—prioritizing reliability, scalability, governance, and cost efficiency while collaborating with cross-functional teams to translate real-world workflows into scalable automation. Beyond modeling, I enjoy designing robust architectures, optimizing inference cost, and building secure, observable AI services that drive measurable business impact. I love mentoring teams, promoting best practices in MLOps, and continuously iterating on prompts, context management, and tool use to deliver grounded, safe, and helpful AI experiences.

Available to hire

Hi, I’m Lalitharani Palakaluri, a Senior AI/ML Engineer focused on building end-to-end AI systems, data pipelines, and GenAI solutions that ground large language models in enterprise data. I’ve led initiatives across data engineering, applied ML, GenAI, RAG, and Agentic AI platforms, delivering production-grade solutions on AWS, Azure, and GCP. I’m passionate about engineering-first AI—prioritizing reliability, scalability, governance, and cost efficiency while collaborating with cross-functional teams to translate real-world workflows into scalable automation.

Beyond modeling, I enjoy designing robust architectures, optimizing inference cost, and building secure, observable AI services that drive measurable business impact. I love mentoring teams, promoting best practices in MLOps, and continuously iterating on prompts, context management, and tool use to deliver grounded, safe, and helpful AI experiences.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

Gen AI Engineer at CVS Health

July 1, 2025 - Present

Collected structured and unstructured data from Snowflake, PostgreSQL, MS SQL Server, PDFs, emails, trade reports, and regulatory documents. Implemented in-database LLM inference, summarization, sentiment analysis, and classification with Snowflake Cortex AI functions. Built scalable ingestion pipelines using Python, PySpark, Databricks (Delta Lake) and Apache Airflow; performed document cleaning, normalization, and metadata tagging. Implemented chunking strategies with LangChain and LlamaIndex for optimal retrieval. Generated semantic embeddings with OpenAI embeddings and SentenceTransformers; stored vectors in Pinecone, FAISS, and Azure Cognitive Search; implemented hybrid retrieval (BM25 + dense vectors). Designed RAG pipelines using LangChain, LlamaIndex, and custom retrievers; developed AI-assisted data transformation using Snowpark + Cortex. Integrated LLMs including GPT-4o, Azure OpenAI, Llama 3, and Mistral. Applied Few-Shot Learning, Chain-of-Thought prompting, and Function Ca

Senior AI/ML Engineer at Lowe's

January 1, 2024 - June 1, 2025

Architected large-scale retail data ingestion pipelines using Python, PySpark, Databricks and Apache Airflow to process high-volume POS transactions, product catalogs (>10M SKUs), pricing feeds, and loyalty data. Integrated structured data from Snowflake, Redshift, and PostgreSQL with unstructured data (supplier contracts, customer reviews). Implemented scalable ETL transformations with Spark SQL, Pandas, and NumPy for real-time and batch analytics. Engineered advanced customer behavioral features (RFM, basket analysis, churn) using Scikit-learn, XGBoost, and LightGBM. Built recommendation engines using Collaborative Filtering, Matrix Factorization, and deep learning approaches. Developed demand forecasting (ARIMA, Prophet) to optimize inventory. Implemented semantic product search via OpenAI Embeddings and SentenceTransformers; built high-performance vector indexing with Pinecone and FAISS; designed a hybrid search: BM25, ElasticSearch, and Dense Vector search. Deployed a RAG-powered

AI Engineer at USAA

August 1, 2022 - December 31, 2023

Designed and implemented an Agentic AI platform to automate complex enterprise workflows requiring reasoning, decision-making, and multi-step execution. Built goal-driven AI agents capable of understanding user intent, task decomposition, and action execution across multiple systems. Implemented multi-agent orchestration using LangGraph, with specialized agents for planning, execution, validation, and retrieval. Integrated Retrieval-Augmented Generation workflows to ground knowledge from enterprise documents and structured data. Implemented vector-based retrieval with Pinecone/FAISS to support contextual reasoning and reduce hallucinations. Designed tool-calling mechanisms using Python and FastAPI for dynamic API/database interactions. Built shared memory and state management to maintain context across multi-step agent interactions. Exposed backend orchestration via FastAPI and Kubernetes; containerized services with Docker; deployed on AWS/Azure with environment-based promotion (dev/t

Data Scientist at Verizon

February 1, 2019 - June 1, 2021

Designed and developed an end-to-end predictive analytics platform using historical and near real-time data. Built data ingestion and feature engineering pipelines from enterprise data lakes and relational databases (Python/SQL). Trained and evaluated supervised models (logistic regression, Random Forest, Gradient Boosting) with Scikit-learn; implemented time-series forecasting (ARIMA, Prophet) to identify trends and anomalies. Performed EDA and statistical validation to quantify feature importance and model performance; integrated evaluation metrics (accuracy, precision, recall, RMSE) for model selection. Deployed models as RESTful inference services using FastAPI for real-time scoring and batch predictions; containerized with Docker; experimented with Azure ML/SageMaker for training runs and controlled deployment. Used MLflow for experiment tracking and model versioning; stored training data in Azure Data Lake and Amazon S3; monitored pipelines with Azure Monitor/CloudWatch. Collabor