AI Software Engineer
I'm a software engineer who enjoys building applications and integrating AI/ML capabilities into them. I’ve started my career working in a startup environment and collaborated with experienced executives, which has given me a mix of hands-on development and exposure to high-level decision-making.
I’m always learning and currently diving deeper into neural networks, large language models (LLMs), and retrieval-augmented generation (RAG), while also starting to explore AI agents.
Potentiam Ltd
Sept 2024 - Present
Working directly with the executive leadership building projects that leverage ML capabilities to meet specific functional requirements and ensuring smooth integration of LLMs into products that serve clients' needs.
Sept 2023 - Sept 2024
Collaborating closely with the Global CIO and Founder/Director of our company, primarily focusing on AI-driven initiatives, while also being mentored to enhance my skills and expertise in the field.
Wipro Ltd
Mar 2023 - Jun 2023
Worked on developing and fine-tuning LLMs using LangChain, implementing a simple Q&A system over documents, optimizing its accuracy, and created an interface using Streamlit.
Deployed and scaled an in-house Private GPT using an open-source model on an Ubuntu server. Configured Nginx reverse proxy, SSL certification, and automated deployment with system services, cron jobs, and log rotation. Enabled remote access via VNC and ensured data privacy by eliminating external AI tools. The solution is now used company-wide, replacing ChatGPT and DeepSeek while maintaining full control over data.
Implemented an AI Search widget for Potentiam Ltd's internal tools, enabling semantic queries beyond traditional keyword matching. Built on a Retrieval-Augmented Generation (RAG) system, the project leveraged FAISS for embedding indexing and LangChain to integrate document retrieval with LLM responses. Improvements included embedding algorithms for speed and accuracy, document-based storage to reduce hallucinations, and caching for query efficiency. Results showed a 90% accuracy rate and reduced user navigation time by 50%, as verified through user feedback and usage metrics.
Developed the "All-in-One Intelligence Framework" for Potentiam Ltd's Talent Acquisition and HR departments, streamlining candidate screening and HR tasks. Key tools included a Resume Reviewer, Job Spec Generator, and Resume Formatter, all leveraging LLMs for detailed analysis, efficient data generation, and conversational interfaces. This improved TA team efficiency, enabling candidate reviews in under 10 seconds and reducing manual data preparation to a 2-3 second response time.
Led the creation of an intelligent chatbot widget for Potentiam Ltd, using Rasa and Flask. Migrated the project from Rasa Open Source to Rasa Pro CALM, incorporating Conversational AI, fallback handling with LLMs, and a redesigned UI. The chatbot significantly improved internal team efficiency by reducing navigation, data retrieval, and exportation tasks to under a minute while demonstrating robust AI integration.
Issued by Amazon Web Services (AWS) - Dec 2024
Issued by Rasa - Aug 2024
Issued by IBM - Mar 2024
Issued by Deeplearning.ai - Feb 2024
Issued by Prepinsta - Dec 2023
Issued by Prepinsta - Oct 2023
Issued by Prepinsta - Aug 2023
Issued by Microsoft and LinkedIn - Jul 2023
Developed this site as documentation of my learning journey into GPT model implementation, inspired by Karpathy's Neural Networks: Zero to Hero series. It covers foundational concepts and advanced transformer-based architectures, serving as both a personal and shared knowledge base.
Building GPT from Scratch: A step-by-step implementation of a GPT-style language model, inspired by Andrej Karpathy’s lecture. The project covers language modeling fundamentals, self-attention mechanisms, and transformer architectures. It starts with a simple bigram model and builds up to a multi-headed self-attention transformer.
A hands-on exploration of character-level language models inspired by Andrej Karpathy's approach. This series covers the development of foundational ML models, the implementation of Multilayer Perceptrons based on seminal research papers, and experimentation with advanced techniques such as backpropagation, language modeling, and neural network concepts, along with an in-depth exploration of PyTorch module implementations.
Built a neural network from scratch by developing a micrograd library, implementing core concepts like backpropagation and gradient descent following Andrej Karpathy’s methodology.
Developed a Portfolio site using Flask, HTML, CSS and JavaScript. Along with a functioning chatbot developed using RASA.
BTech - Computer Science
Grade: 9.32 CGPA
Achievements: Top 10 University Rank Holder in CSE Department, Director of Design at TEDxMVJCE, Vice President at Saahitya Literature Club
PUC - Physics, Chemistry, Math and Computer Science
Grade: 86.5%, Distinction
I.C.S.E - Science
Grade: 92.4%
Achievements: Top Rank Holder in Computer Applications.