Help & Supportcareers@gravityer.com
AI Engineer with less than a year in Machine Learning & Generative AI
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Motivated and detail-oriented aspiring AI/ML Engineer with hands-on experience in machine learning, generative AI, and intelligent backend systems. Proficient in Python, PyTorch, Retrieval-Augmented Generation (RAG), LORA fine-tuning, and vector database technologies. Passionate about developing scalable and impactful AI-driven solutions for real-world applications. Seeking an opportunity to apply technical expertise and contribute to innovation in the field of Artificial Intelligence and Machine Learning.
Pydah College of Engineering
B.Tech · Computer Science and Artificial Intelligence
August 1, 2022 – June 30, 2026
UPSC AI Assistant Open-Source AI Mentor Platform
June 1, 2022 – June 1, 2026
Developed a 100% free and open-source AI mentor platform for Civil Services Examination (UPSC) preparation, addressing the high cost of coaching and information overload faced by aspirants. Architected a Retrieval-Augmented Generation (RAG) pipeline using FastAPI and FAISS to enable semantic search over 100+ PDF notes, allowing aspirants to instantly retrieve relevant study material from large references like Laxmikanth and VisionIAS. Integrated multi-backend LLM support (Groq/Llama 3.1, Gemini, Local GGUF) via a modular service layer. Automated daily current affairs processing using Newspaper3k and Feedparser, classifying news to the relevant GS syllabus section using semantic embedding models.
SymptoSense - AI-Powered Medical Diagnostic Platform
June 1, 2022 – June 1, 2026
Developed an AI-powered medical diagnostic platform that bridges the gap between initial symptom onset and professional medical guidance using a hybrid AI system. Engineered a concurrent multi-agent orchestration pipeline using ThreadPoolExecutor and LangChain to run four specialized AI agents (Clinical, Guidelines, Treatment, Lifestyle) in parallel, reducing total inference time by approximately 60%. Built a custom PyTorch Neural Network with embeddings, BatchNorm, and ReLU layers for disease classification from raw symptom text, serving as the platform's primary diagnostic layer. Integrated a medical report OCR pipeline using DocTR and OpenCV to extract clinical data from PDF and image reports for automated patient history ingestion. Designed a scalable backend using Django REST Framework with Firebase for secure authentication and cloud data persistence.
DSAExplainer Fine-Tuned LLM for DSA Concept Generation
June 1, 2022 – June 1, 2026
Developed a domain-specific fine-tuned LLaMA-3B model using Google Colab to generate structured explanations for Data Structures and Algorithms concepts. Applied LoRA fine-tuning techniques with Python, PyTorch, and Hugging Face Transformers to improve response relevance, clarity, and contextual understanding. Optimized training workflows, prompt engineering, and inference performance within a notebook-based environment. Performed testing, debugging, and iterative refinement to enhance model reliability and output consistency.
AI Associate
Salesforce
June 1, 2026 – Present
Python for Data Science
IBM (EdX)
June 1, 2026 – Present
Generative AI Professional
Oracle
June 1, 2026 – Present
AI Vector Search Professional
Oracle
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's academic projects demonstrate a strong interest in applying AI to real-world problems, including medical diagnostics and educational support, which aligns with an innovative and impact-driven culture. The open-source project indicates a willingness to contribute to the community. However, the lack of professional experience makes it challenging to fully assess cultural fit beyond project alignment.
Soft Skills & Operational Fit
The candidate's project descriptions indicate an ability to work on complex, multi-faceted problems and a drive to create impactful solutions. The open-source project suggests a collaborative mindset. However, without direct work experience or psychometric test results, it's difficult to fully assess operational fit, stress handling, or team collaboration in a professional setting.