Open to opportunities

A B

@ab06

Message

AI engineer building RAG pipelines and conversational NLP systems for fintech use cases.

India

Message

What I'm looking for

I want to build production-grade NLP and RAG systems—tight data pipelines, strong evaluation, and guardrails—especially for fintech-style compliance and real-world messy datasets.

I architected a Zero-Egress, multi-document Enterprise RAG pipeline using Llama-3, ChromaDB, and LangChain, and added Multi-Query Retrieval plus independent RAGAS auditing to cut hallucinations and reach 50% Guardrail Adherence for Fintech compliance.

At APCFSS in Vijayawada, I automated Python-based data extraction and processing for taxpayer datasets, optimizing handling across 100,000 high-dimensional records by 50%. I also built fuzzy address resolution with Levenshtein distance, reducing manual taxpayer identification overhead for 5+ government departments while collaborating across teams to shrink delivery latency by 3 to 4 weeks.

Earlier, I developed a RASA conversational NLP chatbot for regulatory compliance FAQs, improving model confidence from 40% to 80% and hitting an 85% match rate against human baselines, plus high-throughput web scraping infrastructure to feed ML training pipelines.

Experience

Work history, roles, and key accomplishments

Current

Data Analyst and Scientist

Current

APCFSS

Jan 2023 - Present (3 years 7 months)

Engineered automated data extraction and processing pipelines using Python and NumPy, optimizing taxpayer dataset handling by 50% across 100,000 high-dimensional records.

Python NumPy Data Pipeline Architecture