Skip to main content

Shivam Yadav

Building intelligent, scalable, and reliable AI systems for real-world applications.

AI/ML Engineer + GenAI, RAG, AI Agents, and MCP

Scroll to next sectionScroll to next section

About Me

I'm an AI/ML Engineer with experience in building scalable, reliable, and production-ready software systems for real-world applications. My work spans AI/ML, backend development, intelligent automation, and modern data-driven systems, with a focus on creating practical solutions that are efficient, impactful, and built for deployment.

I enjoy solving problems across AI products, backend services, information retrieval, workflows, and system design using modern cloud, data, and application technologies. Outside of work, I also enjoy playing football, which reflects my interest in teamwork, discipline, and consistency.

Get in touch
Shivam Yadav — AI/ML Engineer.

Skills

  • Languages & backend

    • Python
    • FastAPI
    • PostgreSQL
    • MongoDB

  • Cloud

    • Azure
    • AWS
    • AWS Lambda
    • Amazon S3
    • DynamoDB
    • AWS Rekognition

  • Tools / search

    • Azure Cognitive Search
    • Elasticsearch
    • OpenSearch
    • Kibana
    • LLaMA
    • Mistral
    • Ollama
    • Azure OpenAI

  • AI / ML

    • RAG
    • Semantic RAG
    • LLMs
    • AI Agents
    • MCP
    • NLP
    • Multimodal AI
    • OCR
    • Vector Search
    • FAISS

  • Data

    • Databricks
    • ADF
    • Azure Synapse
    • Azure Purview
    • ETL Pipelines
    • Workflow Automation

Projects

Featured project

AutoScrum - AI Powered Workflow Automation System.

Problem

Manual Scrum workflows (requirement analysis, story creation, task allocation) are time-intensive and prone to inefficiencies.

Solution

Developed a multi-agent AI system using MCP that automates requirement analysis, generates structured user stories with acceptance criteria, and performs intelligent task allocation based on team capacity.

Impact

• Reduced manual effort by 50%+ • Accelerated sprint planning and backlog grooming • Improved consistency in user story generation

Tech stack

  • Python
  • FastAPI
  • LangGraph
  • MCP
  • Azure OpenAI
  • PostgreSQL
  • Redis
  • React
GitHub

Experience

  • Associate Software Engineer (AI/ML)

    Unisys · Jul 2024 — Present · Bengaluru

    • Built AI-powered solutions using Semantic RAG, Azure Cognitive Search, NLP, and Multilingual AI for legal and education-focused use cases, improving retrieval efficiency by ~60% and learning outcomes by ~40%.

    • Developed production-grade AI/ML and ETL pipelines with Python, FastAPI, PostgreSQL, ADF, Synapse, Databricks, and Purview for scalable and governed deployment.

    • Designed monitoring dashboards using Elasticsearch and OpenSearch to track performance and operational metrics for 460K+ users.

    • Built a multimodal RAG system for law enforcement applications, supporting audio, video, image, and document intelligence with real-time identification across 100K+ records.

    Tech Stack: Python, FastAPI, Generative AI, AI Agents, RAG, Multimodal AI, Vector Search, OCR, Azure, AWS, Databricks, Elasticsearch, OpenSearch, Kibana.

  • Student Technical Intern (AI/ML)

    Unisys · Jan 2024 — Jul 2024 · Bengaluru

    • Enhanced ingestion and retrieval workflows using Azure Form Recognizer, OCR, semantic chunking, and open-source LLMs.

    • Optimized inference pipelines with LLaMA, Mistral, and Ollama, reducing model inference cost by ~40%.

    Tech Stack: Azure Form Recognizer, OCR, Semantic Chunking, LLaMA, Mistral, Ollama, Python.

Certifications

  • Microsoft Certified: Azure AI Engineer Associate

    Microsoft · Nov 2025 – Nov 2026

    Expertise in designing and deploying AI solutions using Azure AI Services, including NLP, computer vision, and conversational AI.

    View credential

  • Aisera AI Workflows (Intermediate Level)

    Aisera Academy · Mar 2025

    Hands-on experience in building AI-driven workflows, automation, and enterprise AI applications.

    View credential

Contact

Reach out to me via email, social media, or the contact form.

Open contact form