Skip to content
View Nithin00614's full-sized avatar
🎯
Focusing
🎯
Focusing

Organizations

@EvidenceFirst

Block or report Nithin00614

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
Nithin00614/README.md

Hi, I'm Nithin Gowda 👋

AI/ML Engineer · Production AI Systems · RAG · AI Agents · ML Infrastructure

Building reliable AI systems across machine learning, retrieval, LLM orchestration, evaluation and production infrastructure.


🔎 Engineering Focus

I work on the engineering layer between AI models and Production systems, with a focus on reliability, evaluation and scalable system design.

  • RAG & Retrieval — hybrid retrieval, grounding, evaluation, and failure analysis
  • LLM & Agent Systems — LangGraph orchestration, tool use, and multi-agent workflows
  • ML Systems — model serving, evaluation, monitoring, and production inference
  • Backend & Infrastructure — FastAPI, async systems, PostgreSQL, Docker, and CI/CD

⚡ Engineering Highlights

Area Highlight
AI Systems Production RAG · Multi-Agent Workflows · LLM Orchestration
ML Infrastructure ~160 RPS · sub-150ms inference · Async APIs
AI Reliability Retrieval evaluation · Failure attribution · Explainability
Open Source Maintainer @ OpenAgentHQ · AI infrastructure contributions
Research IEEE-published Clinical AI research
  • Explore my pinned repositories below for architecture, implementation, benchmarks, and technical documentation.

🚀 Currently

Founding AI Engineer @ Growthsauras

Working with end-to-end ownership across production AI systems — from architecture and implementation to evaluation, reliability, and deployment.

Maintainer & Active Contributor @ OpenAgentHQ

Contributing to open-source agent infrastructure, developer tooling and production-oriented AI systems.


🌐 Open Source

I actively contribute to open-source AI infrastructure with a focus on agent systems, retrieval reliability, evaluation, and developer tooling.

  • OpenAgentHQ — Maintainer & active contributor
  • Haystack — Retrieval confidence and reliability tooling
  • Contributions across AI evaluation, retrieval diagnostics, and agent infrastructure

🛠️ Technical Stack

AI Engineering & LLM Systems

LangChain    LangGraph    Hugging Face    Milvus    Python

RAG · Agentic Workflows · Tool Calling · Retrieval & Reranking · LLM Evaluation · Guardrails

Backend & API Engineering

FastAPI    PostgreSQL    Redis    JWT    Pydantic

Async Python · REST APIs · Authentication & Authorization · Middleware · Caching · Validation · Error Handling

ML Engineering & Evaluation

PyTorch    Scikit-learn    TensorFlow    MLflow

XGBoost · SHAP · Model Serving · Experiment Tracking · Model Evaluation · Explainability · Drift Detection · Robustness Testing

Production & Infrastructure

AWS    Google Cloud    Vercel    Docker    Render    GitHub Actions

CI/CD · Containerization · Observability · Logging · Monitoring · Load Testing · Production Deployment


🤝 Connect

 

Pinned Loading

  1. Clinical-AI-Decision-Support-System Clinical-AI-Decision-Support-System Public

    Explainable and robust clinical decision support system for chronic kidney disease with ML and GenAI reasoning.

    Python 1

  2. OpenAgentHQ/openagent-eval OpenAgentHQ/openagent-eval Public

    Local-first evaluation framework for RAG systems and AI Agents. 18+ metrics, CLI + SDK, framework-agnostic. The pytest of AI evaluation.

    Python 13 21

  3. Multi-Agent-Market-Intelligence-Layer Multi-Agent-Market-Intelligence-Layer Public

    LLM-Powered Multi-Agent System for Market Intelligence using LangGraph, RAG, and Tool-Based Reasoning to Generate Structured Financial Insights.

    Python 2

  4. Production-Transaction-Risk-Scoring-System Production-Transaction-Risk-Scoring-System Public

    Production-grade ML system for real-time transaction risk scoring with FastAPI, CI/CD, Docker deployment, and load-tested performance (160 RPS, <150ms latency, 0% failure).

    Python 1

  5. Defect-Detection-System Defect-Detection-System Public

    Production-Grade Deep learning system for industrial defect detection using YOLO, featuring real-time inference APIs, model registry, automated retraining pipelines, and Dockerized AWS deployment.

    Python 1

  6. Document-Intelligence-System Document-Intelligence-System Public

    RAG-based document intelligence system with semantic retrieval, grounded Q&A, citations, confidence scoring, and guardrails.

    Python 1