Help & Supportcareers@gravityer.com
AI Engineer with less than a year in Machine Learning & Cloud
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
An enthusiastic and driven individual with a Postgraduate Diploma in Data Science and a Bachelor of Technology in Computer Science Engineering. Possessing strong skills in Python, Machine Learning, Deep Learning, and NLP, with hands-on experience in MLOps tools like FastAPI, MLflow, DVC, Docker, CI/CD, and cloud platforms like GCP and AWS. Successfully delivered an EV Market Segmentation study, built a hospital readmission risk prediction system with automated pipelines, and developed a YouTube RAG chatbot and a zero-shot intent classifier. Eager to contribute to innovative AI and ML projects.
Praxis Tech School
Postgraduate Diploma · Data Science
August 1, 2025 – June 30, 2026
Techno India University
Bachelor of Technology · Computer Science Engineering
August 1, 2019 – June 30, 2023
Feynn Labs
ML Intern
September 1, 2024 – November 30, 2024
India
Zero-Shot Dynamic Routing System
June 28, 2026 – Present
Built a zero-shot intent classifier using BART-large-MNLI across 150 intents, achieving 89% accuracy without labeled training data, matching a TF-IDF + Logistic Regression baseline (88.84%). Engineered a confidence-threshold OOS detection system identifying 100% of 200 out-of-scope queries, reducing misrouting compared to the supervised baseline. Designed a FastAPI service with dynamic label update endpoints, enabling real-time intent updates without retraining.
View ProjectYouTube RAG Chatbot
June 28, 2026 – Present
Built a YouTube RAG chatbot using LangChain, ChromaDB, and GPT-40-mini that fetches video transcripts, chunks and embeds them via HuggingFace MiniLM, and answers user queries through semantic retrieval. Implemented MMR-based retrieval with a strictly grounded prompt template, ensuring all responses are generated exclusively from video context with no external knowledge leakage. Deployed a live Streamlit app with session-state managed chat history and a fully modular RAG pipeline (loader → splitter → embedder → vector store → retriever → LLM).
View ProjectHospital Readmission Risk Prediction
June 28, 2026 – Present
Built an end-to-end healthcare risk prediction system to identify patients with high 30-day hospital readmission risk using a LightGBM-based ML pipeline. Orchestrated automated ETL and model retraining pipelines with Airflow, tracked experiments and models via MLflow + DVC, and implemented data drift monitoring, reducing manual intervention by 90% and enabling weekly model retraining. Deployed a Dockerized FastAPI application on GCP Cloud Run with GitHub Actions CI/CD, achieving 67.7% recall and 64.2% F1-score across 20K healthcare records while enabling fully automated orchestration.
View ProjectMicrosoft Power BI Desktop for Business Intelligence
Udemy
January 1, 2025 – Present
Full Stack Data Science Masters
Ineuron (acquired by Physics Wallah)
January 1, 2023 – Present
Cultural Fit Analysis
The candidate's project portfolio demonstrates a strong interest and practical application in AI/ML, particularly in areas like MLOps, GenAI, and risk prediction, which aligns well with an AI Engineer role. The diversity of projects (healthcare risk prediction, RAG chatbot, zero-shot classification) showcases adaptability and a broad skill set. The candidate's education and certifications further support a commitment to continuous learning in data science and AI. The remote internship experience also suggests flexibility.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a structured approach to problem-solving and an understanding of end-to-end system development. The mention of reducing manual intervention by 90% and enabling weekly model retraining suggests an appreciation for automation and efficiency. Collaboration in a 5-member team for the ML Intern role indicates teamwork experience. However, without direct assessment data, further soft skill evaluation is limited.