Help & Supportcareers@gravityer.com
Generative AI Engineer with less than a year in RAG pipelines & LLM applications.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Final-year B.Tech CSE (AI/ML) student (2026) with hands-on experience designing and deploying Generative AI solutions, Retrieval-Augmented Generation (RAG) pipelines, and Large Language Model (LLM) applications. Proficient in LangChain, OpenAI API, Hugging Face Transformers, vector databases (FAISS, Pinecone), FastAPI, and Docker. Experienced in building end-to-end AI-powered applications, LLM-based chatbots, and cloud-integrated backends. Strong prompt engineering skills with a focus on factual grounding and hallucination mitigation. Eager to contribute to cross-functional teams building production-ready, intelligent applications as a Generative AI Engineer.
AMC Engineering College
B.Tech · Computer Science & Engineering (AI/ML)
August 1, 2022 – June 30, 2026
Christ Academy Junior College
PUC · Class XII
June 1, 2020 – May 31, 2022
Lawrence High School
ICSE · Class X
June 1, 2014 – May 31, 2020
Hospital Readmission Risk Intelligence System
June 1, 2026 – Present
Built an end-to-end ML pipeline using Scikit-learn to predict 30-day hospital readmission risk, covering data ingestion, feature engineering, model training, and evaluation on real-world HMIS patient data. Implemented SHAP-based Explainable AI (XAI) with an automated workflow for per-patient risk driver generation and a Fairlearn fairness audit layer to quantify demographic performance disparities, enabling responsible, bias-aware clinical decision support. Exposed model inference via a FastAPI REST endpoint and designed an interactive Power BI KPI dashboard with real-time risk scoring and drill-down by ward and demographic group, translating model outputs into actionable clinical intelligence for cross-functional stakeholder teams.
AI Drift & Threat Detection System for Cloud Environments
June 1, 2026 – Present
Developed a dual-purpose AI monitoring system combining KDD-based data drift detection and Isolation Forest anomaly detection for real-time cloud threat identification and LLM / ML model performance tracking in dynamic production environments. Engineered automated retraining triggers on statistically significant feature drift, maintaining sustained model accuracy and reliability while reducing manual intervention through intelligent workflow automation. Delivered a unified monitoring dashboard providing centralised LLM health visibility and security alerts, supporting data-driven operational decisions for cloud infrastructure teams.
AI-Powered Financial Document Analyser & QA Chatbot
June 1, 2026 – Present
Architected a production-grade Retrieval-Augmented Generation (RAG) pipeline using LangChain and OpenAI GPT-4, with FAISS vector database for sub-second semantic retrieval across 200+ page financial documents, enabling accurate, context-aware Q&A; with LLM-driven answer generation. Engineered a FastAPI backend with RESTful endpoints for document ingestion, vector index management, and LLM inference orchestration; applied advanced prompt engineering guardrails to ensure factual grounding, eliminate hallucinations, and enforce structured output formatting. Containerised the full application with Docker and delivered a Streamlit-based conversational AI chatbot front-end, enabling non-technical users to query complex financial documents in natural language; collaborated with cross-functional stakeholders to refine chatbot UX and output formatting requirements.
Farmer Crop Loss Early Warning Network
June 1, 2026 – Present
Engineered a multi-source ETL pipeline fusing NASA MODIS/Sentinel-2 satellite NDVI data, IMD weather anomalies, and AGMARKNET crop price data to generate district-level crop stress indices, leveraging Transformer-based time-series encoding and LLM-style attention mechanisms for feature extraction. Applied Facebook Prophet and LSTM deep learning models for time-series anomaly detection, producing a 2-week-ahead crop failure risk score per district through an automated inference workflow. Built a geospatial Power BI dashboard with district-level risk heatmaps, delivering end-to-end AI pipeline ownership and business impact storytelling validated against historical mandi price movements.
Android Developer Virtual Internship
AICTE
June 1, 2026 – Present
UiPath Automation Implementation Methodology Fundamentals (RPA)
UiPath
June 1, 2026 – Present
AI-ML Virtual Internship
AICTE
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's academic projects showcase a diverse range of applications for AI/ML, from financial analysis to healthcare and agriculture, indicating adaptability and a broad interest in applying AI solutions. The emphasis on end-to-end pipeline ownership and business impact storytelling suggests a results-oriented mindset. The candidate's current academic status (final-year student) means they are likely eager to learn and contribute, fitting well into a growth-oriented culture. The projects demonstrate initiative and a proactive approach to learning and applying advanced technologies.
Soft Skills & Operational Fit
The candidate demonstrates strong problem-solving skills through complex project implementations. Their collaboration with cross-functional stakeholders on UX and output formatting indicates good teamwork and communication. The focus on explainable AI and fairness in the Hospital Readmission Risk Intelligence System project suggests a responsible and ethical approach to AI development. The candidate's eagerness to contribute to production-ready applications aligns well with operational goals.