
AI Engineer with 1+ years in Generative AI, Python, and ETL Pipelines
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Computer Engineering graduate with 1 year of industry experience across AI data operations, LLM evaluation, and ETL pipeline workflows at Zensar Technologies, supporting a global client engagement with NVIDIA. Hands-on with Python, SQL, pandas, Generative AI, Agentic AI, LangGraph, Apache Airflow, and Power BI. Built end-to-end data and AI engineering projects independently – spanning data pipelines, machine learning, RAG systems, and analytics dashboards. Eager to contribute across data analytics, data science, and data engineering tracks in a fast-paced, collaborative environment.
Savitribai Phule Pune University
B.E. in Computer Engineering · Computer Engineering
August 1, 2021 – June 30, 2025
Zensar Technologies Pvt. Ltd.
AI & GenAI Data Operations Associate
October 1, 2025 – Present
India
Agentic AI Chatbot - RAG Document Q&A System
January 1, 2024 – June 1, 2024
Built an agentic AI application using LangGraph and Groq Llama 3.3 (70B) with multi-step reasoning workflows for conversational AI and PDF document question answering. Implemented end-to-end RAG pipeline: PDF ingestion → chunking → embedding (FastEmbed BGE-small) → vector storage (pgVector/ChromaDB) → LLM generation with source-cited responses. Applied ML similarity search and retrieval techniques, integrating pgVector with automatic ChromaDB fallback for resilient retrieval across deployment environments. Deployed full Streamlit UI with dark theme, mode switching, PDF upload, and real-time source citations – an independently shipped end-to-end AI application.
View ProjectJob Market Analysis Dashboard
January 1, 2024 – June 1, 2024
Trend & pattern analysis with Python, pandas, and Power BI
MarketPulse - Financial Data Pipeline & Analytics Platform
January 1, 2024 – June 1, 2024
Designed and built an end-to-end ETL data pipeline ingesting 2 years of OHLCV data for 12 equities via yfinance, applying data cleaning and transformation before landing Parquet files in MinIO (S3-compatible bronze data lake). Orchestrated production-style Apache Airflow DAGs with TaskFlow API, IST-aligned scheduling, auto-retries, and XCom-based inter-task data passing for automated daily pipeline runs. Deployed a multi-container Docker stack (PostgreSQL, MinIO, Airflow) – fully reproducible infrastructure enabling scalable, consistent data processing environments. Engineered dbt transformation layer for silver/gold data modeling; built Power BI analytics dashboard to surface equity trends, patterns, and anomalies for business decision-making.
View ProjectFace Detection System
January 1, 2024 – June 1, 2024
Face Detection System - Python, OpenCV, YOLOv3, SQLite
Ignite AI/GenAI Academy
Zensar Technologies
January 1, 2026 – Present
IBM DataOps Methodology
IBM Cognitive Class
January 1, 2025 – Present
AWS Cloud Practitioner Essentials
AWS
January 1, 2024 – Present
Cultural Fit Analysis
The candidate's personal projects demonstrate a strong passion for AI and data engineering, indicating a proactive and self-driven learning approach. The 'Agentic AI Chatbot' project, in particular, shows an interest in cutting-edge AI technologies. The experience at Zensar Technologies and the Ignite AI/GenAI Academy certification suggest an alignment with continuous learning and professional development in the AI domain. However, the candidate is still pursuing a bachelor's degree and has limited professional experience, which might impact their immediate cultural integration into a senior-level role requiring extensive team collaboration and leadership.
Soft Skills & Operational Fit
The candidate's project descriptions indicate an ability to independently ship end-to-end applications, suggesting strong initiative and problem-solving skills. Experience in annotating and quality-assuring LLM outputs implies attention to detail and an understanding of data quality in AI workflows. The mention of 'fast-paced, collaborative environment' in the summary suggests an awareness of operational demands, though direct evidence of collaboration or stress handling is not provided.