About Work Open Source Timeline Skills Certs Connect
Senior Software Engineer, Pegasystems, Bangalore

Raghunath Mahakud

GenAI Engineer / LLM Architect / Agentic AI

Building production AI systems at Pegasystems. From LLM-powered autopilots and multi-agent architectures to NLP platforms at enterprise scale.


About

Turning language into intelligent action

I'm Raghunath Mahakud, a GenAI Engineer with 10+ years of IT experience — 7 years as a Backend Java engineer and 4 years deep in Generative AI, LLMs, and NLP. Currently a Senior Software Engineer at Pegasystems, building the AI systems that power enterprise decisioning at scale.

My focus: LLM fine-tuning, RAG architectures, Agentic AI, and multi-agent systems. I've designed autopilot assistants, production NLP platforms, and IoT microservices for enterprise clients including SoftBank, Mercedes-Benz, and the Government of Rwanda.

Currently pursuing M.Tech in AI & ML at BITS Pilani (WILP), deepening expertise in the theory behind the systems I build every day. Active on Hugging Face — fine-tuning and publishing open-source models, and a member of PyTorch Day India HF.

GenAILLMsRAG SystemsAgentic AIMulti-AgentLangChainFastAPIPrompt EngineeringGPT / Qwen / DeepSeekPythonJavaSpring BootKubernetesKafkaDockerElasticsearch
10+
Years in IT
4+
Years in GenAI
10
Certifications
420+
HF Downloads

Selected Work

Systems built, shipped and scaled

Enterprise-grade systems across GenAI, NLP, IoT, and automotive — built for global clients.

Pega Autopilot — AI Assistant

Pegasystems / 2022 – Present

LLM-driven task orchestration with fine-tuned models, plugin architecture, and multi-step planner agent for enterprise decisioning.

LLM Fine-tuningFastAPILangChainAgentic AIMulti-Agent

Text Analytics NLP Platform

Pegasystems

Production NLP for topic detection and entity extraction with multilingual support serving enterprise clients globally.

Apache UIMAOpenNLPMicronautSVM

IoT Device Management

Ericsson / Client: SoftBank

Geo-redundant platform handling OTA firmware upgrades, diagnostics, and monitoring at scale.

Spring BatchCassandraKubernetesELK

DuKe — Automotive Testing

Mercedes-Benz R&D / Client: Daimler

Microservices migration with event-driven Kafka architecture serving all Mercedes-Benz car testing globally.

KafkaElasticsearchDockerOpenShift

IREMBO e-Government

CrimsonLogic / Client: Govt. of Rwanda

Multi-service e-Government portal with cross-department integration for national service delivery.

Apache CamelSpring BootPostgreSQL

Inferlytics — eCommerce Search

CrimsonLogic

NLP-powered product discovery engine combining domain knowledge graphs with Elasticsearch.

NLPElasticsearchMongoDBKnowledge Graphs

Open Source

GitHub and Hugging Face

Published models, live demos, and learning repositories across the AI/ML open-source ecosystem.

HF
qwen3-eng-odia-translation
Model / 0.8B params

Fine-tuned Qwen3 model for English to Odia translation — 420+ downloads. Published with a companion Spaces demo.

Text Generation420+ downloads
View on Hugging Face →
HF
eng-odia-translation
Space / Live Demo

Interactive Gradio Space — translate English sentences into Odia instantly. Powered by the fine-tuned Qwen3 model.

Live on HF SpacesGradio UI
Try it Live →
GH
LLMs-from-scratch
Repo / Jupyter

Implement a ChatGPT-like LLM in PyTorch from scratch — deep understanding of transformer internals.

Jupyter Notebook
View on GitHub →
GH
DeepSeek_From_Scratch
Repo / Jupyter

DeepSeek implemented from scratch to understand MoE, attention mechanisms, and modern LLM architecture internals.

Jupyter Notebook
View on GitHub →
GH
all-agentic-architectures
Repo / 17+ Patterns

Implementation of 17+ agentic architecture patterns — from ReAct and tool-use to multi-agent orchestration systems.

Jupyter Notebook
View on GitHub →
GH
advanced_finetuning_bootcamp
Repo / LLM

Advanced fine-tuning techniques — LoRA, QLoRA, full fine-tuning, and optimization strategies for any LLM.

Jupyter Notebook
View on GitHub →
GH
kafka_mcp_server
Repo / MCP

MCP (Model Context Protocol) server for Apache Kafka — enabling AI agents to interact with Kafka infrastructure.

Python
View on GitHub →
GH
rag_sessions
Repo / RAG

Collection of different RAG techniques — naive RAG, advanced retrieval, re-ranking, hybrid search, and evaluation.

Python
View on GitHub →

Career Path

10+ years of building at scale

2025 – Present
M.Tech — Artificial Intelligence & Machine Learning
BITS Pilani (WILP) / Expected 2027
Advanced AI/ML coursework — deepening expertise in the models and architectures driving modern GenAI systems.
Mar 2022 – Present
Senior Software Engineer — Decisioning & AI
Pegasystems India Pvt. Ltd. / Bangalore
Leading GenAI engineering — Autopilot AI assistant, production NLP pipelines, LLM function-calling infra. Python, FastAPI, LangChain, Java, Micronaut.
Jan 2020 – Mar 2022
Senior Software Developer
Ericsson Global Services / Bangalore
IoT Device Management for SoftBank — geo-redundant architecture, OTA upgrades, Kubernetes deployments, ELK monitoring.
Nov 2017 – Dec 2019
Senior Consultant
Mercedes-Benz Research & Development India / Bangalore
Microservices migration for DuKe automotive testing platform — Kafka, Elasticsearch, Docker/OpenShift/Kubernetes.
Sept 2015 – Oct 2017
Senior Software Engineer
CrimsonLogic Pte. Ltd. / Bangalore
e-Government services for Rwanda (IREMBO) and Inferlytics NLP-powered eCommerce search engine.

Expertise

Skills and tech stack

Deep stack spanning Generative AI, distributed systems, and production engineering — 10+ years across 4 enterprise domains.

AI
Generative AI
LLM Fine-tuning
RAG Systems
Agentic / Multi-Agent
Prompt Engineering
FW
LLM Frameworks
LangChain
FastAPI
GPT / Qwen / DeepSeek
FAISS / Vector DBs
NL
NLP
Apache UIMA / OpenNLP
Entity Extraction
Topic Modelling
TensorFlow / MALLET
BE
Backend Engineering
Java / Spring Boot
Python
Micronaut
Apache Kafka
DO
DevOps & Cloud
Kubernetes / Helm
Docker / OpenShift
AWS
Jenkins / CI/CD
DB
Databases
Elasticsearch
PostgreSQL / Oracle
MongoDB / Cassandra
FAISS / Vector DBs

Credentials

Technical certifications

10 verified credentials across GenAI, NLP, RAG, RL, and enterprise architecture.

01
AI Evals for Everyone
LevelUp Labs / Apr 2026
02
OpenClaw Mastery for Everyone
LevelUp Labs / Apr 2026
03
Reinforcement Learning for LLMs
The RAG Pack / Mar 2026
04
Building Your First AI Agent Using N8N
AnalytixLabs / Apr 2025
05
Modern AI Pro (Practitioner)
Mitra Robot / Nov 2024
06
Modern AI Pro (Essentials)
Mitra Robot / Oct 2024
07
NLP with Classification & Vector Spaces
Coursera / Oct 2023
08
Introduction to TensorFlow for AI, ML & DL
Coursera / Aug 2023
09
Generative AI with Large Language Models
Coursera / Jul 2023
10
Certified System Architect (CSA)
Pegasystems / Apr 2022

Get In Touch

Let's build something intelligent

Open to GenAI consulting, LLM architecture discussions, and enterprise AI collaborations.

Email
mahakudraghunath298@gmail.com
LinkedIn
raghunath-mahakud
GitHub
github.com/raghu298
HF
Hugging Face
huggingface.co/raghu298

Whether it's about Agentic AI architectures, LLM fine-tuning, or scaling production NLP systems — I'd love to connect. Member of PyTorch Day India HF community.