Professional Experience

Dailoqa

AI/ML Engineer
Apr 2025 – present | Noida, India
  • •Designed a modular, multi-agent RAG infrastructure enabling contextual document retrieval and reflective dialogue, integrating vector and graph-based retrieval to support relationship-aware query resolution across 20K+ sessions, reducing retrieval latency by 40%.
  • •Built a Model Context Protocol (MCP) layer across the application, streamlining tool calling and enabling seamless orchestration between agents and external APIs, improving modularity and reducing integration overhead by 35%.
  • •Engineered a cloud-agnostic ingestion framework that processed over 10K documents from Azure Blob, AWS S3, and local storage; implemented semantic chunking and dynamic index routing, improving retrieval precision by 30% for hybrid queries.
  • •Delivered a containerized FastAPI backend via Docker for consistent local and cloud deployments (Azure, AWS), reducing environment configuration overhead by 70% and enabling <5-minute deployment cycles in production and dev environments.
  • •Implemented multi-layered safeguards for user-agent interactions — including prompt injection prevention, toxic content detection, and role-based access control (RBAC) — resulting in a 95% reduction in unsafe or malformed queries across production logs.
  • •Managed and mentored a team of 3 engineers, coordinating development sprints and code reviews to ensure timely delivery of high-quality features.

    • Stealth Startup

    AI Engineer
    Jan 2024 – Apr 2025 | Remote
  • •Built a Helpdesk Assessment Feature, generating detailed CRM reports (Jira, Salesforce) by categorizing 5M+ tickets into topic-based groups for streamlined queries.
  • •Automated knowledge article creation from cases, training AI Agents to cut LLM token costs and boost query resolution efficiency by 30%.
  • •Reduced customer query times using AI-trained knowledge articles, improving response accuracy by 20% and lowering costs.
  • •Designed Multi-AI Agent workflows with LangGraph, enhancing collaboration and workflow efficiency by 25%
  • •Built a Retrieval-Augmented Generation (RAG) system, slashing info retrieval time from 10-15 mins to <1 min, boosting efficiency by 90%.
  • •Led Elite Robots’ EC series arm project, collecting 100GB+ data and integrating InfluxDB with 50+ tags for real-time monitoring and Python-based parameter control.
  • •Fine-tuned LLMs for domain-specific datasets, enhancing model performance.
  • •Developed and optimized document extraction pipelines for unstructured PDFs and scanned files, enabling high-accuracy text and metadata retrieval for downstream AI workflows, reducing manual review time by 60%.

    • National Institute of Technology Trichy (NIT Trichy)

    Summer Intern
    May 2023 – Jul 2023Trichy, Remote
  • •Conducted 6+ months of network lateral movement research, identifying and mitigating threats, and publishing actionable insights.
  • •Explored advanced cybersecurity techniques (cyber deception, anomaly detection) using machine learning, reducing false positives by 15% and improving incident response efficiency.
    • Education

    Oriental Institute of Science and Technology

    2020 – 2024 | Bhopal

    Bachelor of Technology (B.Tech) - Computer Science and Engineering - (Data Science) GPA-8.65

    Projects
  • •Created a Python library for data scientists, speeding up ML model selection and evaluation by 25%.
  • •Published on PyPI, achieving 1,000+ downloads with seamless pip install integration.

    • AI Assess

    Python, Streamlit, FastAPI, OpenAI, LangChain, PyPDF2
  • •Developed an AI tool for educators, generating 10+ customizable MCQs/subjective questions from PDFs or keywords with adjustable difficulty.
  • •Built a FastAPI backend and Streamlit frontend, automating answer evaluation for 30% faster query resolution and real-time scoring.
  • •Improved evaluation accuracy by 20% with robust normalization for inconsistent inputs.
  • •Engineered a Retrieval-Augmented Generation (RAG) system with a fine-tuned LLM, integrating hybrid search (vector embeddings + BM25 keyword search) to boost query relevance by 35% and cut retrieval time by 50%.
  • •Optimized retrieval with semantic chunking, multi-query expansion, and cross-encoder reranking, improving context precision by 40% for complex queries.
  • •Deployed a FastAPI REST interface with dynamic caching and load balancing, enhancing cross-platform accessibility by 80% and ensuring scalability.
    • Publications (60+ Citations)
    Skills
    Programming: Python, Java, Cypher Query Language, SQL
    AI/ML: LangGraph, PyTorch, Agentic AI, HuggingFace, NLP, Generative AI, LLMs, MCP.
    Tools: Git/GitHub/Gitlab, CI/CD, Docker, Linux, SQLite, Neo4j, FastAPI, RAGAS, Graph Databases, Vector Databases, ChromaDB, Pinecone
    Libraries: Streamlit, Llama-Index, Pandas, NLTK, PyPDF2, PyMuPDF, Crew AI, scikit-learn, FastAPI
    Cloud: Microsoft Azure, Azure AI Foundry, Amazon AWS.
    Certificates