AI Engineer with less than a year in conversational AI and machine learning.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Entry-level AI Engineer / Machine Learning Engineer with hands-on experience developing conversational AI systems and machine learning applications. Skilled in Python, prompt engineering, RAG, LangChain, FAISS, and transformer models. Developed and deployed a production-grade AI chatbot via FastAPI enabling real-time natural-language queries. Seeking to apply NLP and generative AI expertise to enhance customer support solutions.
Savitribai Phule Pune University
B.E. · Artificial Intelligence & Machine Learning
August 1, 2022 – June 30, 2026
NV Analytical Solutions
Machine Learning Intern
January 1, 2025 – June 1, 2025
India
RAG-Based YouTube Chatbot
June 24, 2026 – Present
Architected an end-to-end Retrieval-Augmented Generation (RAG) pipeline to enable intelligent Q&A over YouTube video transcripts. Engineered complete document ingestion workflow including text chunking, embedding generation, and semantic retrieval using LangChain. Integrated vector databases (FAISS/Chroma) for efficient similarity search and context retrieval. Designed prompts and fine-tuned a transformer-based LLM using Hugging Face Transformers to improve answer relevance and accuracy.
Demand Forecasting MLOps Pipeline
June 24, 2026 – Present
Engineered a production-ready end-to-end MLOps pipeline for e-commerce demand forecasting, training and comparing 4 models (LinearRegression, RandomForest, XGBoost, Prophet) with time-based 80/20 splits, and registering the best model to MLflow Model Registry with automated metric logging (RMSE, MAE, R2, MAPE). Built a FastAPI REST service with /predict, /health, and /monitoring/report endpoints; containerized the full stack using Docker Compose (API + MLflow server); and implemented GitHub Actions CI/CD to automate testing, model retraining, and Docker Hub deployment on every push to main. Integrated Evidently AI for data drift monitoring with auto-retraining trigger when drift score exceeds 0.3; managed data versioning with DVC and feature engineering pipeline generating temporal, lag, and rolling-window features across 28-day historical windows.
Cultural Fit Analysis
The candidate's projects showcase a strong interest and practical application in cutting-edge AI/ML domains, aligning well with an AI Engineer role. The diversity of projects, from conversational AI chatbots to demand forecasting MLOps pipelines, indicates a broad technical curiosity and willingness to tackle different challenges. Their experience with open-source tools and frameworks suggests a collaborative mindset. The focus on production-readiness in their projects also aligns with industry best practices.
Soft Skills & Operational Fit
The candidate demonstrates strong problem-solving skills through their project work, particularly in designing end-to-end MLOps pipelines and RAG systems. Their ability to integrate various tools and frameworks (e.g., Docker, GitHub Actions, MLflow) suggests good operational awareness. The detailed project descriptions indicate a structured approach to development. However, without direct interaction or psychometric test results, assessing stress handling, teamwork, and communication clarity in a collaborative setting is not possible.