Help & Supportcareers@gravityer.com
AI Engineer with less than a year in Generative AI and LLM Application Development
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
B.Tech (AI/ML) engineer with hands-on experience building production-style Generative AI applications, including a FastAPI backend that orchestrates a Retrieval-Augmented Generation (RAG) pipeline over a vector store and prompts a Llama-3.3-70B LLM for contextual responses. Skilled across the GenAI stack – Python, LangChain, prompt engineering, embeddings, vector databases, and REST APIs – with additional full-stack (Next.js, PostgreSQL) and classical machine learning / deep learning (CNN, NLP, Computer Vision) experience gained through internships and independent research projects.
RV University
B.Tech · Artificial Intelligence and Machine Learning
August 1, 2023 – June 30, 2027
Sri Chaitanya Techno School
Class XII (CBSE)
N/A – May 31, 2023
Kendriya Vidyalaya
Class X (CBSE)
N/A – May 31, 2021
Samaksha Technology
SDE Intern
June 1, 2026 – Present
India
Dhee AI Research Centre, RV University
AI Research Intern
June 1, 2025 – July 31, 2025
India
SmartDrive — High-Throughput Concurrent Data Ingestion Pipeline
May 1, 2026 – May 31, 2026
Engineered a production-grade concurrent ingestion pipeline using a Producer-Consumer architecture and ThreadPoolExecutor to download and process high-volume cloud assets asynchronously. Implemented fault-tolerant API integration utilizing exponential backoff with random jitter to handle strict provider rate limits and ensure pipeline stability. Built a multi-tenant data isolation layer secured via Google OAuth 2.0, routing processed text chunks into a ChromaDB vector store for low-latency semantic RAG search.
View ProjectEmpathia - Multilingual Therapeutic AI with Dynamic State Extraction
April 1, 2026 – June 30, 2026
Built a high-throughput FastAPI backend leveraging a RoBERTa zero-shot classifier for real-time state extraction and multi-label intent mapping from raw user prompts. Designed a low-latency Retrieval-Augmented Generation (RAG) pipeline, managing session embeddings via a vector database to optimize semantic context extraction. Engineered a persistent multi-turn conversational architecture to overcome LLM context-window limitations, lowering token consumption while preserving long-term application state.
View Project32Fit - Predicting Fitness Progress Using Machine Learning
June 1, 2025 – August 31, 2025
Conducted original domain research to mathematically map physiological variations in muscle and fat composition relative to structured exercise and lifestyle variables. Formulated mathematical growth curves to fit physiological trends, integrating a secondary Random Forest classifier pipeline to predict noise variations induced by non-linear lifestyle factors. Owned the full project lifecycle — from proprietary data collection and hybrid regression/classification modeling to branding — achieving 91% (bulking) and 93% (fat-loss) predictive accuracy.
View ProjectSOFA-Scanpath_Optimization_and_Fatigue_Evaluation
June 1, 2025 – June 30, 2026
Developed a CNN-LSTM deep learning model to predict human eye-tracking scanpaths and quantify visual fatigue in graphic design, achieving 0.022 validation loss. Curated a novel gaze-pattern dataset from original research comparing designer vs. non-designer attention to automate data-driven optimization for digital layouts.
View ProjectAffective Computing & Emotional Intelligence
Indraprastha Institute of Information Technology, Delhi
January 1, 2023 – Present
Cultural Fit Analysis
The candidate's diverse project portfolio, ranging from therapeutic AI to fitness prediction and sign language recognition, demonstrates a broad interest in applying AI to various domains. Their involvement in university clubs and hackathon mentorship indicates a collaborative spirit and willingness to contribute to a technical community. The target role of 'AI Engineer' aligns well with their demonstrated skills and project focus, suggesting a good cultural fit for an innovation-driven environment.
Soft Skills & Operational Fit
The candidate's project descriptions highlight strong problem-solving skills, particularly in overcoming technical challenges like LLM context-window limitations and handling API rate limits. Their involvement in leadership activities (Design Lead, Hackathon mentorship) suggests good collaboration and communication potential. The ability to own full project lifecycles indicates strong organizational and execution capabilities.