Open to opportunities

AASTHA rani

@aastharani

Message

Data Scientist and AI Engineer building scalable Generative AI, RAG, and agentic workflows.

India

Message

What I'm looking for

I’m looking to build enterprise-scale Generative AI with RAG and agentic workflows—pairing strong evaluation and MLOps with responsible innovation—so real-world problems turn into measurable business impact.

I’m a Data Scientist and AI Engineer with 4 years of experience transitioning from classical machine learning to advanced Generative AI. I build intelligent, enterprise-scale systems using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) pipelines, vector databases, and advanced NLP techniques to drive practical, responsible business innovation.

I architect and optimize RAG and agentic AI workflows with LangChain and LangGraph, and I take ownership of evaluation, monitoring, and performance optimization—boosting Generative AI deployments by up to 30%. I’ve developed ML pipelines improving predictive accuracy by 15–22%, reduced deployment time by 30% using MLOps practices, and delivered an HR RAG assistant that improved information accessibility by 40% while cutting manual data handling time by 50%.

Experience

Work history, roles, and key accomplishments

Current

Data Scientist (LLMs)

Current

Cedcoss Technologies

Jan 2024 - Present (2 years 5 months)

Architected and delivered enterprise GenAI solutions, including LLM-based RAG and agentic workflows, boosting deployment accuracy/robustness/scalability by up to 30%. Built and optimized scalable backend services integrating embeddings, vector databases, and LLMs with evaluation/monitoring frameworks to improve system performance.

LLM Retrieval Augmented Generation (RAG)LangGraph Vector Databases Embeddings NLP MLOps

GenAI System Engineer

Tata Consultancy Services

Oct 2021 - Dec 2023 (2 years 2 months)

Developed end-to-end machine learning pipelines and advanced deep learning models, improving predictive accuracy by 15% and model robustness/data quality by 20%. Delivered GenAI/MLOps workflows with FastAPI-based deployments, reducing deployment time by 30% while improving performance using standard ML metrics and cross-validation.