Skip to main content
Pavan GangadharPG
Open to opportunities

Pavan Gangadhar

@pavangangadhar

I build AI agents with LLMs—RAG, multi-agent systems, and production deployment for real workflows.

India
Message

What I'm looking for

I’m looking for a role where I can build reliable LLM and AI agent systems—RAG, multi-agent workflows, and prompt strategies—while shipping production deployments with strong observability and AI safety guardrails.

I’m an AI Agent Developer building LLM-powered systems at Oracle, focused on automating complex workflows across APIs, databases, and external tools. I design Retrieval-Augmented Generation (RAG) solutions using vector databases like FAISS and Pinecone to deliver context-aware, accurate responses for enterprise use cases.

I implement multi-agent architectures for planning, coordination, and execution using LangChain, LangGraph, and other agent frameworks. I optimize prompt engineering to improve reasoning and reduce hallucinations, integrate agents with backend services via REST APIs and microservices, and manage context and memory for long-running performance.

I also bring strong production and reliability practices—deploying AI services with FastAPI, Docker, and Kubernetes, and adding observability with logging and evaluation pipelines. On top of that, my earlier software and ML internships (including TensorFlow-based image recognition) keep me grounded in building end-to-end products that work well in real environments.

Experience

Work history, roles, and key accomplishments

Oracle logoOR
Current

DevOps Consultant

Aug 2024 - Present (1 year 11 months)

Worked as a DevOps Consultant at Oracle.

Oracle logoOR
Current

Ai agent Developer

Aug 2024 - Present (1 year 11 months)

• Designed and developed AI agents using LLMs to automate complex workflows, enabling intelligent task execution across APIs, databases, and external tools
• Built Retrieval-Augmented Generation (RAG) systems using vector databases (FAISS/Pinecone) to provide context-aware, accurate responses for enterprise use cases
• Implemented multi-agent architectures for task planning, coordination, and exec

Tata Elxsi logoTE

Engineer Intern

Jan 2024 - Jul 2024 (6 months)

Interned as a Software Developer in iOS Development, focusing on enhancing client applications.
worked on the UI revamp for a client project, implementing modern design principles and improving user experience.
Worked with Swift and Xcode to develop and optimize features for seamless functionality.
Collaborated with a dynamic team to deliver high-quality, user-centric solutions.
Gained hands-on ex

CogXR Labs logoCL

App Developer

Sep 2022 - Jun 2023 (9 months)

Internship involved developing machine learning models utilizing TensorFlow for image recognition tasks, specifically focused on the detection of medical conditions like COVID-19, viral pneumonia, lung cancer, and tuberculosis from chest X-ray images. These models were subsequently integrated into a software application designed for local deployment on mobile devices, including Android and iOS pla

AutoCar logoAU

Mobile Application Developer

May 2022 - Oct 2022 (5 months)

During the internship, I was tasked with developing a software application that served as a mobile counterpart to the company's existing website. This application aimed to replicate and encompass all the functionalities and features present on the website.

Education

Degrees, certifications, and relevant coursework

DB

Dayananda Sagar College of Engineering, BANGALORE

Bachelor of Engineering - BE, Computer Science

2021 - 2024

Dayananda Sagar College of Engineering logoDE

Dayananda Sagar College of Engineering

Bachelor of Engineering, Computer Science

2021 - 2024

Bachelor of Engineering (BE) in Computer Science at Dayananda Sagar College of Engineering from 2021 to 2024.

Get matched with your dream remote job

Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan