Help & Supportcareers@gravityer.com
AI Engineer with hands-on experience building LLM-powered applications, RAG systems, and deep learni
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Generative AI and AI Engineer with hands-on experience building LLM-powered applications, Retrieval-Augmented Generation (RAG) systems, and deep learning solutions from Proof-of-Concept (POC) to scalable cloud deployment. Proficient in Python, FastAPI, NLP pipelines, and AWS infrastructure. Experienced in designing RESTful services, optimizing model performance, and developing production-ready AI systems using embeddings and vector search for semantic retrieval.
Sri Venkateswara College of Arts and Computer Science (Autonomous)
Bachelor of Business Administration (BBA) · Business Analytics
August 1, 2022 – June 30, 2025
Multi-Agent AI Assistant Platform with MCP, RAG & Agent Orchestration
June 1, 2026 – Present
Designed and developed a multi-agent AI platform consisting of Research, Coding, Flight Booking, and Image Generation agents with an intelligent routing engine for dynamic task execution. Implemented MCP-based tool integration and API orchestration, enabling secure communication between LLMs, external services, databases, and domain-specific tools. Built a RAG-powered coding assistant using document retrieval and vector search, improving response relevance through semantic retrieval from custom knowledge bases. Developed an AI image generation pipeline using Stable Diffusion, prompt enhancement with local LLMs, and semantic context retrieval for image quality and consistency.
Medical AI Model for Brain Tumor Classification using CNN (95% Accuracy)
June 1, 2026 – Present
Cleaned a 2,500-image MRI dataset — removed corrupt and misclassified images, balanced class distribution across all four categories (glioma, meningioma, pituitary, no tumor), and applied feature engineering before an 80/20 train/test split. Designed a CNN architecture with Global Average Pooling, achieving 95% validation accuracy and reducing validation loss by 20%. Evaluated model performance using precision, recall, F1-score, and confusion matrix; deployed inference using FastAPI, Docker, and GitHub Actions CI/CD.
LLM-Powered RAG Chatbot with Semantic Search & AWS Deployment (FAISS, FastAPI)
June 1, 2026 – Present
Built a Retrieval-Augmented Generation (RAG) chatbot using Sentence Transformers and FAISS for semantic search and context-aware responses. Designed a dual-mode intelligence pipeline serving two query intents from a single FAISS-indexed backend: institutional (course fee, duration, certification, prerequisite and post-course learning path) and research (on-demand AI/ML concept explanations) with top-5 semantic chunk retrieval. Implemented prompt compression to reduce per-query LLM token cost — designed with real client budget constraints in mind, not as an optimisation afterthought. Technologies: Python, FastAPI, FAISS, Sentence Transformers, AWS EC2.
Artificial Intelligence & Machine Learning Certification
Digital Edify Technologies Pvt. Ltd.
June 1, 2026 – Present
DevOps with AWS Certification
Digital Edify Technologies Pvt. Ltd.
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's portfolio demonstrates a strong initiative and passion for AI, evidenced by several complex personal projects. The projects cover diverse areas within AI, including computer vision, NLP, and agentic AI, which aligns well with an innovative and research-oriented culture. The focus on practical deployment and optimization (e.g., prompt compression, CI/CD) suggests a results-driven mindset. The candidate is currently pursuing a BBA in Business Analytics, which, while not a traditional CS degree, could bring a valuable business-oriented perspective to technical solutions. The lack of professional experience makes a deeper cultural fit assessment challenging.
Soft Skills & Operational Fit
The candidate's project descriptions highlight an ability to work with real-world constraints (e.g., prompt compression for token cost reduction) and apply SDLC principles to AI projects, suggesting a practical and disciplined approach. The diversity of projects (medical imaging, multi-agent systems, RAG chatbots) indicates adaptability and a broad interest in AI applications. However, without direct work experience or psychometric test results, it's difficult to fully assess stress handling, team collaboration, or other soft skills.