Skip to content
View Srinath279's full-sized avatar

Block or report Srinath279

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Srinath279/README.md

Srinath Siddamsetty

🤖 Senior AI/ML Engineer · Agentic AI · GenAI · LLMOps

Building production-grade LLM platforms & multi-agent systems @ Verizon

LinkedIn Location Open to Work


👨‍💻 About Me

I'm a Senior AI/ML Engineer specializing in Agentic AI, GenAI, and LLMOps at Verizon. I architect and ship production-scale multi-agent systems, LLM evaluation pipelines, and RAG platforms that handle real enterprise workloads — not just demos.

🎯 What sets me apart: I bridge the gap between cutting-edge AI research and reliable, observable, production systems.


🔧 Tech Stack

🧠 AI / ML

Python PyTorch MLflow HuggingFace

🤖 Agentic AI & LLM Frameworks

LangChain LangGraph Google ADK MCP FastAPI

☁️ Cloud Platforms

GCP Vertex AI BigQuery Cloud Run Cloud Storage AWS

⚙️ MLOps & Pipelines

Apache Airflow Kubeflow Vertex AI Pipelines MLflow Tracking DVC

🛠️ Infrastructure & DevOps

Docker Kubernetes GKE GitHub Actions


🚀 What I Build

Domain What I Deliver
🤖 Multi-Agent Systems Production orchestration with LangGraph & ADK, agent memory, tool-use, MCP integrations
📊 LLMOps & Evaluation Evaluation harnesses, observability pipelines, prompt versioning, CI/CD for LLMs
🔍 RAG Architectures Production vector search, retrieval evaluation, grounding, and hallucination reduction
⚙️ ML Pipelines End-to-end pipelines with Airflow & Kubeflow, feature stores, model versioning with DVC & MLflow
☁️ ML Platform Engineering Scalable model serving on GKE/Cloud Run, Vertex AI pipelines, experiment tracking

🌟 Featured Projects

Project What It Does Impact
🤖 agent-sandbox LLM multi-agent orchestration experiments with LangGraph & MCP Agentic AI · LangGraph
🧠 pytorch-DL Deep learning from scratch: CNNs, ResNet, Transfer Learning PyTorch · Computer Vision
📈 mlflow Production MLflow server with auth & cloud secrets on GCP MLOps · Docker · GCP
☸️ k8s Kubernetes deployment of a live ML-powered Streamlit app K8s · GKE · MLOps

📫 Let's Connect

💼 I'm open to Senior AI/ML Engineer, Staff ML Engineer, and AI Platform Lead roles.

Reach me on LinkedIn — always happy to talk AI, agents, and LLMOps.

LinkedIn

Pinned Loading

  1. agentmemory agentmemory Public

    Forked from rohitg00/agentmemory

    #1 Persistent memory for AI coding agents based on real-world benchmarks

    TypeScript

  2. hermes-agent hermes-agent Public

    Forked from NousResearch/hermes-agent

    The agent that grows with you

    Python

  3. agent-sandbox agent-sandbox Public

    Forked from agent-sandbox/agent-sandbox

    Agent-Sandbox is an E2B compatible easy-to-use enterprise-grade sandboxes for AI Agents. Allows Agents to securely run untrusted LLM-generated Code, Browser use, Computer use, and deploy Website etc.

    Go

  4. agent-skills agent-skills Public

    Forked from addyosmani/agent-skills

    Production-grade engineering skills for AI coding agents.

    Shell

  5. deer-flow deer-flow Public

    Forked from bytedance/deer-flow

    An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

    Python