Skip to content
View iarjunganesh's full-sized avatar
🎯
Focusing
🎯
Focusing
  • Swedbank AB
  • Stockholm, Sweden
  • 23:37 (UTC +02:00)
  • LinkedIn in/iarjunganesh

Block or report iarjunganesh

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
iarjunganesh/README.md

Typing SVG

NVIDIA Certified Professional: Agentic AI (NCP-AAI)

Hack for Good Winner


🧠 About Me

Senior engineer with 13+ years building distributed systems, cloud-native platforms, and enterprise software across banking, media, and regulated environments.

My background spans backend engineering, platform modernization, cloud-native architecture, and large-scale operational systems. Today, I focus on applying Agentic AI and AI governance patterns to real-world enterprise workflows where explainability, auditability, and operational reliability matter.

🏦 Software Engineer @ Swedbank
πŸ€– Exploring Agentic AI, Azure AI Foundry, Foundry IQ, A2A and MCP
πŸ—οΈ Passionate about Distributed Systems, Platform Engineering and AI Governance


πŸš€ Featured Builds

Backblaze Generative Media Hackathon 2026

WIP Solo entry

CI Coverage Release License: MIT Watch Video

Spotify Wrapped β€” but for your bank account. An agentic pipeline that turns a transaction CSV into a personalized 60-second narrated recap video.

Backblaze B2 Genblaze GMI Cloud NVIDIA NIM OpenAI FFmpeg Semantic Kernel Plaid

React Next.js Node.js Vercel

Python FastAPI Railway

Live Demo Jupyter Demo

🧠 Continuum

CockroachDB Γ— AWS Hackathon 2026

WIP Solo entry

CI Coverage Release License: MIT Watch Video

Agentic incident-response memory that survives the agent being killed mid-incident β€” execution state persists in CockroachDB, not process memory, so a cold-started agent resumes from the exact interrupted step.

CockroachDB Amazon Bedrock AWS Lambda MCP

Gradio

Python 3.14 FastAPI

Live Demo

πŸ›‘οΈ ARGUS

Microsoft Agents League @ AI Skills Fest 2026

Hack for Good Winner Shipped Solo entry

Tests Coverage Release License: MIT Demo

Multi-agent compliance intelligence platform on Azure AI Foundry β€” KYC, AML, and risk investigation through transparent, evidence-backed, auditable decisions.

Azure AI Foundry Azure OpenAI GPT-4o Foundry IQ Azure AI Search Cosmos DB Semantic Kernel A2A RAG MCP

Gradio

Python 3.11


πŸ“‚ All Projects

Project Description Stack Status
Banker's Wrapped 🎬 AI-Powered Financial Storytelling β€” agentic pipeline that turns transaction CSVs into personalized 60s recap videos via NVIDIA NIM, Genblaze, and Backblaze B2 Python FastAPI Semantic Kernel NVIDIA NIM Genblaze Next.js 🚧 Hackathon WIP
Continuum 🧠 Agentic incident-response memory that survives the agent being killed mid-incident β€” execution state persists in CockroachDB for cold-start recovery Python FastAPI CockroachDB Amazon Bedrock AWS Lambda MCP 🚧 Hackathon WIP
ARGUS πŸ›‘οΈ Agentic Risk & Governance Unified Screening β€” Multi-agent compliance intelligence platform with transparent, auditable, evidence-backed decision making Azure AI Foundry A2A RAG Semantic Kernel πŸ† Hack for Good Winner
pythonic-algorithms-lab ⚑ CPU/GPU algorithm implementations (sorting, graphs, DP, data structures) with benchmarking infrastructure & Dash dashboard Python CUDA Dash NumPy βœ… Active

πŸ€– What I Work On

🧩 Agentic AI & Enterprise Intelligence

Designing AI systems using Azure AI Foundry, Foundry IQ, multi-agent orchestration, Agent-to-Agent (A2A) communication, RAG with hybrid search, document intelligence, and reasoning-driven workflows β€” focused on building AI that is explainable, grounded, and production-ready.

πŸ—οΈ Distributed Systems & Backend Architecture

13+ years building scalable platforms with Java (Spring Boot, Quarkus) and Python (FastAPI), cloud-native architectures, microservices, NoSQL databases, event-driven systems, and hybrid cloud across AWS, Azure, and OpenShift.

βš™οΈ AI Infrastructure, Performance & Compute

Exploring the infrastructure layer behind modern AI β€” GPU computing, NVIDIA CUDA, model serving, vector search, observability, and performance engineering.

πŸ“‘ Reliability, Observability & Platform Engineering

Designing resilient systems with Azure Functions, Service Bus, OpenTelemetry, Application Insights, KQL, and operational telemetry pipelines that support enterprise-grade reliability and governance.


🎯 Current Focus

πŸ€– Agentic AI

  • Multi-Agent Architectures
  • Azure AI Foundry
  • Foundry IQ
  • MCP
  • A2A Communication

🏦 Enterprise AI

  • Compliance Intelligence
  • KYC & AML Workflows
  • AI Governance
  • Auditability
  • Human Oversight

βš™οΈ Engineering

  • Distributed Systems
  • Platform Engineering
  • Cloud Native Architecture
  • Observability
  • Reliability Engineering

πŸ› οΈ Tech Stack

Languages & Frameworks

Java Python Spring Boot Quarkus FastAPI Next.js

Agentic AI & LLM

Azure AI Foundry Semantic Kernel RAG A2A NVIDIA NIM Genblaze Amazon Bedrock

Cloud & Infrastructure

Azure AWS AWS Lambda OpenShift Azure Functions Service Bus Backblaze B2 CockroachDB Railway Vercel

Observability, AI Infra & Data

OpenTelemetry Application Insights KQL NVIDIA CUDA Vector Search NoSQL Event Driven


πŸ’Ό Career Journey


2025 – Present
Β  Software Engineer
Anti-financial crime Β· Secure banking systems Β· AML platforms
2021 – 2025 Β  Senior Java Developer
Media & metadata systems Β· Content Engineering Β· Streaming platforms
Mar–Sep 2021 Β  Software Developer
2012 – 2021
8 yrs 6 mos
Β  Multiple Roles Β· India & Australia






πŸ“Š GitHub Stats

Β 


πŸ“œ Certifications

10+ Professional Certifications including:


🀝 Let's Connect

Β 

Building trustworthy AI systems that explain their reasoning, leave an audit trail, and actually work in production.
If that's the kind of problem you're working on β€” I'd love to talk.

Pinned Loading

  1. argus argus Public

    ARGUS β€” Agentic Risk & Governance Unified Screening | Multi-agent KYC system powered by Azure AI Foundry + Foundry IQ | Microsoft Agents League Hackathon 2026 β€” Reasoning Agents track

    Python

  2. q1729 q1729 Public

    Ramanujan's mathematics meets the NVIDIA stack: CUDA-Q/cuQuantum quantum simulation + NIM/Nemotron analysis, consumer RTX to cloud H100

    Python

  3. continuum continuum Public

    Agentic incident-response memory that survives the agent being killed mid-incident β€” CockroachDB Γ— AWS Hackathon 2026

    Python

  4. bankers-wrapped bankers-wrapped Public

    Banker's Wrapped β€” AI-Powered Financial Storytelling Platform | Backblaze Generative Media Hackathon 2026

    Python

  5. pythonic-algorithms-lab pythonic-algorithms-lab Public

    Algorithm implementations with CPU vs GPU benchmarking, empirical Big-O profiling, and an interactive Dash dashboard. CuPy + Numba CUDA kernels with CPU fallbacks.

    Python

  6. llm-qlab llm-qlab Public

    Python