Jahnavi Poloju

Data Engineer - AI/ML | LLM & RAG Specialist

LinkedIn | GitHub | Email | Phone

[email protected]

8919998905

Remote, US

About

Highly accomplished Data Engineer with a strong focus on AI/ML, bringing expertise in developing and deploying advanced data pipelines and intelligent systems. Proven ability to automate complex ETL processes, enhance data completeness by 30%, and leverage LLMs and NLP for sentiment analysis and data enrichment, driving significant improvements in business intelligence and operational efficiency. Seeking to apply cutting-edge AI/ML and data engineering skills to build scalable, high-impact solutions in a forward-thinking technology environment.

Work Experience

Data Engineer - AI/ML

Claris, an Apple company - contracted through TechnoApex.ltd

Aug 2024 - Jun 2024

Remote, N/A, US

Led the development and deployment of AI/ML-driven data pipelines and automation solutions to enhance marketing intelligence and customer insights for Claris, an Apple company.

  • Automated cross-channel data ETL processes, replacing manual reporting and reducing Business Intelligence (BI) workload by 70% for the Marketing team.
  • Engineered and deployed robust ETL pipelines in Python with Airflow, integrating data from diverse RESTful APIs and building interactive Grafana dashboards to enhance campaign visibility.
  • Developed an AI data enrichment tool using Google API and Crawl4AI, achieving a 30% increase in CRM data completeness for improved segmentation and analytics workflows.
  • Designed structured prompts for precise entity extraction, minimizing hallucination, and implemented async processing with Pydantic for high-quality, field-level data use.
  • Developed and deployed AI-driven data pipelines for sentiment and topic modeling of community data, utilizing advanced NLP techniques (LDA, BERTopic) and OpenAI APIs to enable real-time tracking of customer concerns.

Education

Civil Engineering

Indian Institute of Technology Kharagpur (IITKGP)

7.45/10

Nov 2020 - May 2024

Kharagpur, West Bengal, IN

Projects

Multi-Agent Research Assistant for Annual Report Analysis

Dec 2024 - Jun 2025

Developed a sophisticated RAG-powered system leveraging LLMs and multi-agent collaboration to parse, summarize, and analyze complex company financial reports.

Conversational Web Search Tool

Nov 2024 - May 2025

Designed and deployed a RAG-based assistant leveraging OpenAI and Serper APIs to retrieve web data and generate natural language responses for enhanced user interaction.

Undergraduate Research - Deep Learning

Aug 2023 - May 2024

Conducted research on physics-informed neural networks (PINNs) using TensorFlow to model and analyze structural elements, advancing capabilities in computational mechanics.

Languages

English

Skills

Programming Languages

  • Python
  • SQL
  • JavaScript

AI/ML & Data Science

  • LangChain
  • scikit-learn
  • Tensorflow
  • LDA (Gensim)
  • BERTopic (UMAP, HDBSCAN, c-TF-IDF)
  • Physics-Informed Neural Networks (PINNs)
  • LLMs
  • RAG
  • NLP
  • Pydantic
  • MLflow

Data Engineering

  • AirFlow
  • ETL
  • Data Pipelines
  • API Integration
  • Web Scraping
  • Vector Stores (FAISS, ChromaDB)
  • Async Processing

Frameworks & Libraries

  • FastAPI
  • RESTful APIs
  • Flask
  • Streamlit
  • PyMuPDF

Developer Tools & Cloud

  • Git
  • Azure
  • VS Code

Business Intelligence

  • Tableau
  • Grafana