
AI Engineer with 1+ years in RAG pipelines & intelligent agents
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Backend Developer with 1.4 years of experience specializing in AI-driven automation and retrieval systems. Proven track record in building production-grade RAG (Retrieval-Augmented Generation) pipelines and intelligent agents using Python, FastAPI, and LangChain. Expert in integrating LLMs (GPT-4) with vector databases like ChromaDB and cloud ecosystems including Azure and GCP. Skilled at designing conditional workflows that bridge the gap between automated AI responses and human-in-the-loop oversight.
Yeshwantrao chavan college of engineering nagpur
Bachelor Of Technology · Information Technology
August 1, 2021 – June 30, 2024
RSSGK Agrawal School and Jr. College, Tumsar
Higher Secondary School
June 1, 2019 – May 31, 2020
LTIMindtree
Technical Consultant
December 1, 2024 – Present
Pune, Maharashtra, India
Intelligent Healthcare Report Analysis and Recommendation System
June 25, 2026 – Present
Designed and implemented an advanced healthcare AI solution leveraging the CrewAI Agentic framework to automate the analysis of blood reports in PDF format, processing reports with 98% accuracy. The system extracts critical health data, generates a concise and interpretable summary of values, and provides tailored dietary recommendations and actionable suggestions to patients based on their health metrics. Combined natural language processing, data extraction, and domain-specific recommendation algorithms to improve preventive healthcare practices, impacting over 500 patients in pilot testing.
AI-Powered Document Query System
June 25, 2026 – Present
Developed a system enabling users to upload and process PDFs and Word documents, converting and storing them in a vector database with 99% accuracy. Implemented semantic search capabilities, allowing users to query document content with response times under 2 seconds for datasets exceeding 1 million records. Integrated a large language model (LLM) to provide contextually relevant responses.
MCP-Based Natural Language SQL Query System
June 25, 2026 – Present
Developed an intelligent query system using FastMCP Server and Gemini AI to convert natural language into SQL for seamless interaction with a PostgreSQL database. Created custom MCP tools and schema resources to support function calling, dynamic SQL execution, and safe data retrieval. Enabled Gemini AI to interpret schema and return precise tool calls, with human-readable explanations of query results. Designed a lightweight MCP client-server architecture supporting modular integration and real-time response generation.
Cultural Fit Analysis
The candidate's academic projects demonstrate a strong interest in diverse AI applications, from healthcare to document processing and database interaction. Their professional experience at LTIMindtree further solidifies their practical application of AI in enterprise solutions. The breadth of technologies and tools listed (Python, FastAPI, LangChain, various LLMs, vector databases, cloud platforms) indicates adaptability and a willingness to learn new systems, which is a good cultural fit for dynamic AI engineering roles. The academic background in Information Technology with relevant coursework in OOP, Databases, Data Structures, and Cloud Computing provides a solid theoretical foundation.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a problem-solving mindset and an ability to translate complex requirements into functional AI solutions. The focus on accuracy (98% for healthcare reports, 99% for document processing) and performance (sub-2-second response times) suggests an attention to detail and operational efficiency. The mention of 'human in the loop' features and conditional workflows points to an understanding of practical deployment challenges and the need for controlled automation.