• Over 6+ years of experience in Design and Development, and implementation of various client-server enterprise applications in Python using a web framework like Flask, FastAPI and hands-on experience in developing and deploying data analytics and complex AI/ML models in various domains.
• Knowledge in various ML techniques such as regression, classification, clustering, Decision Trees and deep learning, Generative AI.
• Developed projects using Techniques like (RAG) Retrieval Augmented Generation, fetch the required data from vector DB.
• Hands-on experience on GenAI, LLM (Anthropic Claude, OpenAI, OLLaMA, GrooqAI, PandasAI, BambooLLM, AzureAI), Langchain, OpenAI API(chatgpt-4, fine-tune), NLP, GooglePaLM, LLaMA.
• Developed a RAG project using LangChain and Llama Index. (Indexing for vector db, similarity search in langchain).
• Good knowledge of converting PDF data to structured text into chunks and storing it in vector format into vector DB.
• Worked on Ollama using LangChain and Langserve and created APIs in FastAPI Framework.
• Good experience in Pandas, numpy, matplotlib libraries for data cleaning and pre-processing.
• Fine-Tuned pre-trained model for better accuracy and efficiency such as HuggingFace, BERT model.
• Have a knowledge of evaluation of RAG and diff. AI Model and how to optimize then using fine-tuning or improving RAG architecture.
• Have worked on some projects which involved NLP techniques (NLTK library) such as Tokenization, Part-of-speech (POS) tagging, Sentiment Analysis, Text Classification, Text-to-Speech.
• Good knowledge of OOPs (Object Oriented Programming) and applying Object-Oriented principles in the Software Development Life Cycle.
• Experienced in Backend applications using FastAPI/Flask and SQL/MySQL Well versed with the design and development of the presentation layer for web applications using technologies like HTML5, CSS3, and JavaScript.
• Possess good communication, interpersonal and analytical skills, and a highly motivated team player with the ability to work independently and Team environments.

• Thinking of the different Machine Learning approaches and techniques according to the Business domain.
• Have a good command over data cleaning and preprocessing techniques on large datasets.
• Build Efficient Machine learning models. Can fine-tune the existing model for the needs and requirements and achieve good results.
• Gathering requirements and translating the business details into Technical design.
• Experience with various AI/ML supervised & unsupervised algorithms/models such as SVM, Decision Trees, Random Forest, K-NN, CNN, RNN, GAN
• Development of Python APIs for Mobile Apps and JS based Frameworks like ReactJS, AngularJS, etc.
• Involved in Developing RESTful & micro-services using Python frameworks.
• Performed troubleshooting, fixed and deployed many Python bug fixes for two main applications that were the main source of data for both customers and internal customer service team.
• Wrote and executed various MySQL database queries from Python using Python-MySQL connector.
• Followed the Agile methodology to develop the application.
• Using the GIT version control tool to coordinate team-development.
• Maintained and updated the application following the client requirement.
• Involved in organizing meetings to know the needs of clients for the Enterprise solution Implementation.

Languages/Scripting: Python, AI/ML, LLMs, FastAPI, Server-level configurations, Data Structures, HTML, CSS, JavaScript

Python Frameworks: Flask, FastAPI

Artificial Intelligence (AI): RAG (Retrieval Augmented Generation), GenAI (pipelines), Machine Learning (ML), Deep Learning (DL), Natural Language Processing (NLP), Large Language Models (LLMs): OLLaMA, Anthropic Claude, OpenAI (GPT 3.5 & 4), GooglePaLM, LLaMA, Whisper AI

ML Libraries: Pandas, NumPy, TensorFlow, PyTorch, scikit-learn

Web Services: REST API

Databases: MySQL, PostgreSQL

Tools: Git, Docker

Cloud Server: AWS

Project Management Systems (PMS): Jira, Slack

Operating Systems: Linux Variants, Windows Variants

Q&A and Appointment Scheduling System Using AI (Automatic Voice Bot):

Tech Stack:

• AI/ML: RAG, LangChain, OpenAI (ChatGPT), Whisper ASR AI, NLP
• Databases: Neo4J, Postgres
• Frameworks/Tools: TensorFlow, Scikit-learn, Twilio, Redis, Django, RestAPI (DRF)
• Cloud: AWS

Description:

• Developed a VoiceBot using OpenAI and RAG for business inquiries where users can call via Twilio and ask questions or schedule appointments.
• Trained and fine-tuned a Large Language Model (LLM) with a business-specific knowledge base using OpenAI (fine-tuning GPT 3.5 and 4).
• Implemented RAG with LangChain to create a custom LLM, generating vectors from the updated database and storing them in vector databases like Milvus and ChromaDB.
• Automated appointment scheduling based on user conversations with AI, booking appointments on the user’s preferred date and time.
• Leveraged Neo4J Graph Database to enhance contextual understanding by running Cypher queries to find related topics from the user's query.
• Integrated PostgreSQL with the custom LLM to retrieve updated data and manage database entries for complex queries.
• Utilized LangChain, OpenAI, and various services to build a custom voice bot that meets specific business requirements.

DB Talk (Communicate With Your Database):

Tech Stack:

• AI/ML: OpenAI, GrooqAI, HuggingFace LLM, LangChain, PandasAI, AzureAI, FewShotLearning, BambooLLM, Google Palm, ChatGoogleGenerativeAI
• Frameworks/Tools: Streamlit, PyTorch, FastAPI, Docker
• Databases: MySQL, Mixtral

Description:

• Developed an AI-powered solution for intuitive database communication, simplifying data management and interactions. Features include easy access to database information, a chat-based interface for seamless querying, and elimination of complex query syntax.
• Utilized advanced AI models such as OpenAI, GrooqAI, HuggingFace LLM, LangChain, BambooLLM, PandasAI, and ChatGoogleGenerativeAI to enhance natural language processing and interaction capabilities.
• Employed FewShotLearning to handle diverse data types and queries with minimal training, improving system adaptability.
• Implemented Docker for containerization, ensuring consistent deployment and scalability.
• Designed a user-friendly interface using Streamlit for an interactive and intuitive user experience.
• Improved productivity and streamlined data management by simplifying database interactions, making them more user-friendly and less technical.

Text-to-Image and Video Application:

Tech Stack:

• AI Models: Sable Diffuser, Flux Koda, Black Forest/FLUX, DALL-E, ByteDance, AnimateLCM
• Frameworks/Tools: Streamlit, FastAPI, LangChain

Description:

• Developed an advanced application to transform user-generated creative prompts into high-quality images and videos.
• Enabled users to customize outputs by selecting content type (image or video), adjusting quality settings, and choosing from various size options for precise alignment with their creative vision.
• Employed cutting-edge AI models such as Sable Diffuser, Flux Koda, Black Forest/FLUX, and DALL-E to generate diverse and visually appealing content.
• Designed an interactive user interface with Streamlit for a seamless and engaging user experience, allowing users to create and preview image/video content.
• Integrated FastAPI for backend processing to ensure rapid and efficient handling of user requests and prompt generation.
• Leveraged LangChain to manage data flow and interactions between the user interface and AI models, enhancing system responsiveness and performance.

Chat With PDF and URL (AI):

Tech Stack:

• AI/ML: LangChain, OpenAI (ChatGPT), HuggingFace, GoogleBERT, Mixtral, Bloom
• Data Processing: Bs4, FAISS, ChromaDB, RAG
• Programming/Cloud: Python, AWS

Description:

• Developed a system enabling users to interact with web content and PDF documents through a conversational interface, simplifying information extraction from various sources.
• Integrated advanced AI models including HuggingFace, OpenAI, GoogleBERT, Mixtral, and Bloom to deliver accurate, context-aware responses, ensuring a seamless conversational experience.
• Employed Bs4 to scrape and extract web content, processing it for efficient retrieval and interaction, while handling diverse and dynamic data sources.
• Implemented RAG (Retrieval-Augmented Generation) using LangChain, with FAISS and ChromaDB managing data structures for quick, relevant responses to user queries.
• Deployed the system on AWS to ensure scalability and reliability, supporting multiple concurrent user interactions and accommodating increased demand as needed.

Electronic and Fashion Recommendation for E-commerce Site:

Tech Stack:

• Techniques/Tools: Cosine Similarity, F1 Score, Collaborative Filtering

Description:

• Developed a recommendation system for electronic and fashion items based on user preferences and past behavior.
• Utilized cosine similarity and F1 score to ensure recommendation accuracy, with data sourced from the Amazon dataset.
• Conducted data preprocessing to clean and transform the dataset, handling missing values and removing irrelevant or duplicate data for efficient modeling.
• Employed a collaborative filtering technique to analyze user behavior and the behavior of similar users, generating personalized recommendations.
• Computed cosine similarity between users and items, recommending items most similar to those previously liked by the user.
• Evaluated system performance using the F1 score, which combines precision and recall to measure the effectiveness of the recommendation system in predicting user preferences.