AI Engineer with less than a year in Machine Learning & Deep Learning.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Aspiring Data Science and AI Engineer with hands-on experience in Machine Learning, Deep Learning, Data Analytics, and Agentic AI systems. Skilled in building predictive models, deep learning-based medical image classification systems, retrieval-augmented generation (RAG) pipelines, and multi-agent voice AI platforms using Python, LangGraph, and FastAPI. Experienced in CNN-based architectures, transfer learning, explainable AI techniques such as Grad-CAM, and end-to-end conversational AI systems for real-world applications in healthcare, business analytics, and logistics.
Indian Institute of Information Technology Dharwad (IIITDWD)
B.Tech · Data Science and Artificial Intelligence
August 1, 2021 – June 30, 2025
AI - Agentic Voice AI for Logistics
June 1, 2026 – June 30, 2026
Built a logistics intelligence platform combining a custom business logic layer (Haversine-based distance engine, warehouse assignment, GST-compliant pricing engine) with a multi-agent LLM architecture. Designed a Retrieval-Augmented Generation (RAG) knowledge base using ChromaDB and local embeddings, indexing company policies, FAQs, and service documents for grounded, semantic question answering. Architected a LangGraph-based multi-agent orchestrator with dedicated Pricing, Distance, and Knowledge agents, including conversation memory and intelligent query routing. Exposed full functionality through FastAPI REST endpoints and WebSocket streaming for real-time, token-by-token conversational responses. Integrated Deepgram for streaming speech-to-text and ElevenLabs for text-to-speech, enabling an end-to-end voice conversation pipeline for incoming phone calls. Implemented structured logging with Loguru and a test suite covering core business logic, ensuring reliability and observability across the system.
Brain Tumor Detection using Deep Learning (CNN + Grad-CAM)
April 1, 2026 – May 31, 2026
Developed an end-to-end deep learning system to classify brain MRI scans into Glioma, Meningioma, Pituitary, and No Tumor categories. Implemented transfer learning using multiple CNN architectures including VGG16, ResNet50, and MobileNetV2 for performance comparison. Resolved model collapse issues by optimizing training strategy, including staged training with frozen base layers followed by selective fine-tuning. Achieved a best test accuracy of 91.6% using VGG16 with balanced classification across all tumor classes. Integrated Grad-CAM for model interpretability, visualizing tumor regions and improving trust in predictions for medical applications.
Data Science Course
Besant Technologies, BTM Layout
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's projects demonstrate a strong alignment with an AI Engineer role, covering both traditional deep learning (medical imaging) and cutting-edge generative AI/LLM applications (agentic voice AI). The diversity in project domains (logistics, healthcare) indicates adaptability and a broad interest in applying AI. The academic background in Data Science and AI further strengthens the cultural fit for an AI-focused organization. However, the candidate's experience level is entry-level, which might require mentorship within a senior team.
Soft Skills & Operational Fit
The candidate's resume highlights 'Communication, Problem-solving, Team Collaboration, Documentation' as soft skills. The project descriptions are clear and detailed, indicating good communication. The nature of the projects, especially the multi-agent system, suggests an ability to tackle complex problems and potentially collaborate. However, without direct interview data or peer feedback, the operational fit and depth of these soft skills cannot be fully assessed.