Technical Skills

Real-World Need: Every industry — from healthcare to finance — is adopting AI tools for automation, content creation, and decision support. Proficiency in multiple AI platforms is essential for modern tech roles.

How I Learnt: Self-exploration across ChatGPT, Gemini, and Copilot. Completed certifications in GenAI and prompt engineering. Applied tools in academic projects for writing, coding, and data analysis.

Real-World Need: Gemini is Google's flagship multimodal AI, used in enterprise content workflows, data analysis, and creative industries for rapid ideation and production-grade outputs.

How I Learnt: Used Gemini extensively for AI-powered story writing and screenplay generation. Experimented with iterative prompt refinement to maximize creative output quality.

Real-World Need: AI-native development environments are transforming software engineering — enabling faster prototyping, automated debugging, and intelligent code generation at scale.

How I Learnt: Built this entire portfolio website using Antigravity IDE. Hands-on daily use for HTML/CSS/JS development, leveraging its AI-assisted coding capabilities.

Real-World Need: Prompt engineering is a core skill for anyone working with LLMs — from building chatbots and search systems to automating business workflows and generating precise, structured outputs.

How I Learnt: Certified via Simplilearn (GitHub Copilot course). Applied techniques in story writing with Gemini and academic automation tasks. Continuous practice refining prompt clarity and structure.

Real-World Need: Linear algebra underpins neural networks, computer graphics, recommendation systems, and data transformations. It is the mathematical language of AI.

How I Learnt: Studied during Semester 2 at J.N.N Institute of Engineering. Applied concepts in understanding how ML models process data through matrix operations and transformations.

Real-World Need: Probability powers everything from A/B testing and risk assessment to Bayesian ML models and natural language processing uncertainty quantification.

How I Learnt: Academic coursework supplemented by self-study. Applied statistical reasoning to understand model evaluation metrics and data distribution analysis.

Real-World Need: Calculus is essential for understanding gradient descent, backpropagation in neural networks, and optimizing loss functions — the core engine of model training.

How I Learnt: University coursework in engineering mathematics. Connected theory to practice by studying how optimizers like Adam and SGD use derivatives to minimize error.

Real-World Need: Optimization algorithms are the backbone of training every AI model — from tuning hyperparameters and resource allocation to logistics and operations research.

How I Learnt: Explored through academic studies and self-learning how gradient-based methods drive model convergence and performance improvement in ML pipelines.

Real-World Need: C remains foundational for embedded systems, OS development, IoT devices, and performance-critical applications. Understanding C builds strong low-level programming intuition.

How I Learnt: Core academic curriculum in Semester 1. Practiced through lab exercises, algorithm implementations, and understanding memory management fundamentals.

Real-World Need: C++ powers game engines (Unreal), high-frequency trading systems, robotics, and competitive programming. Its OOP and STL capabilities make it versatile for complex systems.

How I Learnt: Learnt during Semester 2 coursework. Built on C foundations to understand OOP concepts — classes, inheritance, polymorphism — and practiced with STL data structures.

Real-World Need: Python is the dominant language in AI/ML, data science, web backends, and automation. Its ecosystem (NumPy, Pandas, TensorFlow) makes it indispensable for modern tech.

How I Learnt: Self-taught and academic coursework. Used for scripting, automation tasks, and AI/ML exploration. Building practical projects to deepen understanding.

Real-World Need: The web is built on HTML/CSS/JS. Every frontend role, web app, and digital product relies on these core technologies for structure, styling, and interactivity.

How I Learnt: Built this entire portfolio from scratch using vanilla HTML, CSS, and JS. Hands-on learning through designing responsive layouts, animations, and interactive components.

Real-World Need: GitHub is the industry standard for code collaboration, version control, CI/CD pipelines, and open-source contribution. Every developer uses it daily.

How I Learnt: Managing project repositories, tracking code changes, and hosting this portfolio. Learning branching, pull requests, and collaborative workflows for team projects.

Real-World Need: VS Code is the most popular code editor in the world, used across web development, data science, and DevOps. Its extension ecosystem and integrated terminal make it the go-to IDE for professional developers.

How I Learnt: Daily driver for all coding work — HTML/CSS/JS, Python scripts, and C/C++ projects. Learned keyboard shortcuts, Git integration, debugging workflows, and extension management through consistent hands-on use.

Real-World Need: Jupyter Notebooks are the standard tool for data scientists and analysts — used for exploratory data analysis, creating reproducible research, building ML pipelines, and presenting findings with inline visualizations.

How I Learnt: Learnt during a Data Analyst Bootcamp. Used notebooks for hands-on data exploration, writing Python analysis code, creating visualizations, and documenting analytical workflows step-by-step.