Abhishek Yadav

AI Researcher

Gwalior, Madhya Pradesh, India3 yrs 2 mos experience

Most Likely To SwitchAI Enabled

Key Highlights

Led development of AI-powered document verification platform.
Architected multi-agent system for seamless database interactions.
Developed machine learning approach for plant disease detection.

Stackforce AI infers this person is a Machine Learning Engineer specializing in AI-driven SaaS solutions.

Contact

Skills

Core Skills

Machine LearningArtificial Intelligence (ai)Large Language Models (llm)Deep Learning

Other Skills

Amazon Web Services (AWS)Artificial Neural NetworksAzure Document IntelligenceBERT (Language Model)ChatGPTChatbotsComputer ScienceComputer VisionConversational AIConvolutional Neural Networks (CNN)Data ScienceData StructuresDjangoFine TuningFull-Stack Development

About

I'm a computer programmer with an avid interest in Data Structures, Algorithms and Optimization. As a core programmer, I love taking challenges and love being part of the solution. Solid Programming expertise in Python, Machine Learning and Web Development . Enthusiastic team player, a fast learner with creative problem solving skills, good coding and communication skills.

Experience

Nexus verify

2 roles

Machine Learning Engineer(Gen AI)

May 2024 – Present · 1 yr 10 mos · Remote

Led the end-to-end development and successful deployment of Nexus, a production-grade AI-powered document
verification platform for construction submittals, serving multiple enterprise clients with 99.5% uptime and
processing over 10,000 documents monthly.
Architected a sophisticated RAG (Retrieval-Augmented Generation) pipeline integrating Azure Document
Intelligence with custom vector embeddings and dual similarity search mechanisms, achieving 95% accuracy in
extracting critical information from complex multi-page construction PDFs and technical specifications.
Spearheaded the fine-tuning of various open source model on a curated dataset construction knowledge,
optimizing for domain-specific terminology, entity recognition, and compliance checking, resulting in 40%
improvement in accuracy over base models and 60% reduction in hallucinations.

Machine LearningArtificial Intelligence (AI)RAGAzure Document IntelligenceVector Databases

Machine Learning Engineer Intern(Gen AI)

Feb 2024 – Apr 2024 · 2 mos · Remote

Large Language Models (LLM)RAGArtificial Intelligence (AI)Vector DatabasesAmazon Web Services (AWS)Prompt Engineering

Thereliableai

Machine Learning Engineer

Jan 2024 – Apr 2024 · 3 mos · Greater Bengaluru Area · Remote

Architected and deployed a multi-agent system on AWS using LangGraph to enable GPT-4 language interactions with databases, incorporating agents for clarification, SQL query generation, data retrieval, and insights, facilitating seamless conversational access to structured data.
Explored and integrated various large language models, including Mistral 7B, LLaMA 70B, and GPT-4, into the multi-agent system, leveraging their strengths in natural language understanding, query generation, and insight derivation, while optimizing for performance and cost-effectiveness through model selection and fine-tuning strategies.

Artificial Intelligence (AI)LangGraphLarge Language Models (LLM)RAGMachine LearningVector Databases+1

Trovex.ai

Machine Learning Engineer

Sep 2023 – Dec 2023 · 3 mos · Greater Bengaluru Area · Remote

Developed and implemented a Q-A (Retrieval-Augmented Generation) application utilizing GPT and Langchain technologies; seamlessly integrated the system into a scalable Django API for production, enabling real-time responses and enhancing user experience.
Added multiple use cases in a chatbot using GPT for enhanced functionality.
Works on a vector database similar to ChromaDB and Pinecone.
Works on FIne-tuning the open source models

Machine LearningLarge Language Models (LLM)Artificial Intelligence (AI)Conversational AIPrompt EngineeringGPT-3

Madhav institute of technology and science, gwalior

Research Intern

May 2023 – Aug 2023 · 3 mos · On-site

1) Development of Machine learning based approach for plant disease detection.
2) Trained various models, including VGG16, ResNet, and Inception, to classify diseases in leaves of different crops, such as tomatoes, corn, and apples.

Deep LearningArtificial Intelligence (AI)Image Processing