RaghunathMahakud.
Java Backend Engineer
Senior Software Engineer, Pegasystems
I'm Raghunath Mahakud, a GenAI Engineer, LLM Architect, and Backend Java Engineer from Bangalore, India. With 10+ years of experience, I build production AI systems — from LLM-powered autopilots and multi-agent architectures to NLP platforms at enterprise scale.
About Raghunath Mahakud
Hello! I'm Raghunath, 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 is 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) and actively publishing open-source models on Hugging Face (420+ downloads). Member of PyTorch Day India HF.
A few technologies I've been working with recently:
- Java & Python
- LangChain / FastAPI
- RAG & Vector Search
- Agentic / Multi-Agent
- GPT / Qwen / DeepSeek
- Kafka & Kubernetes
Core Identity
Experience & Education
Professional Experience
Senior Software Engineer
- Lead GenAI engineering for the Pega Autopilot AI assistant — LLM-driven task orchestration with fine-tuned models and a multi-step planner agent.
- Built production NLP pipelines and LLM function-calling infrastructure for enterprise decisioning.
- Stack: Python, FastAPI, LangChain, Java, Micronaut, Agentic & Multi-Agent systems.
Senior Software Developer
- Built IoT Device Management for SoftBank — a geo-redundant platform handling OTA firmware upgrades, diagnostics, and monitoring at scale.
- Designed geo-redundant architecture with Kubernetes deployments and ELK monitoring.
- Stack: Spring Batch, Cassandra, Kubernetes, ELK.
Senior Consultant
- Led microservices migration for the DuKe automotive testing platform serving all Mercedes-Benz car testing globally.
- Architected an event-driven Kafka pipeline with Elasticsearch analytics.
- Stack: Kafka, Elasticsearch, Docker, OpenShift, Kubernetes.
Senior Software Engineer
- Built e-Government services (IREMBO) for the Government of Rwanda — a multi-service portal with cross-department integration.
- Developed Inferlytics, an NLP-powered eCommerce product discovery engine.
- Stack: Apache Camel, Spring Boot, PostgreSQL, Elasticsearch, NLP.
Education
M.Tech — AI & Machine Learning
- Advanced AI/ML coursework, deepening the theory behind the systems I build every day.
- Focus areas: deep learning, model architectures, and the mathematics driving modern GenAI.
Global Consumer Intelligence (GCI)
- Completed the GCI program focused on AI, Machine Learning, Data Science, and data-driven marketing strategy.
- Hands-on with Python for data analysis, modeling, and consumer-intelligence applications on real-world business problems.
Things I've Built
Pega Autopilot — AI Assistant
Pegasystems · 2022 – Present
LLM-driven task orchestration with fine-tuned models, plugin architecture, and a multi-step planner agent for enterprise decisioning.
- LLM Fine-tuning
- FastAPI
- LangChain
- Agentic AI
- Multi-Agent
Text Analytics NLP Platform
Pegasystems
Production NLP for topic detection and entity extraction with multilingual support, serving enterprise clients globally.
- Apache UIMA
- OpenNLP
- Micronaut
- SVM
IoT Device Management
Ericsson · Client: SoftBank
Geo-redundant platform handling OTA firmware upgrades, diagnostics, and monitoring at scale.
- Spring Batch
- Cassandra
- Kubernetes
- ELK
DuKe — Automotive Testing
Mercedes-Benz R&D · Client: Daimler
Microservices migration with event-driven Kafka architecture serving all Mercedes-Benz car testing globally.
- Kafka
- Elasticsearch
- Docker
- OpenShift
IREMBO e-Government
CrimsonLogic · Client: Govt. of Rwanda
Multi-service e-Government portal with cross-department integration for national service delivery.
- Apache Camel
- Spring Boot
- PostgreSQL
Inferlytics — eCommerce Search
CrimsonLogic
NLP-powered product discovery engine combining domain knowledge graphs with Elasticsearch.
- NLP
- Elasticsearch
- MongoDB
- Knowledge Graphs
Open Source Contributions
qwen3-eng-odia-translation
Fine-tuned Qwen3 model for English → Odia translation. Published with a companion Spaces demo.
eng-odia-translation
Interactive Gradio Space — translate English sentences into Odia instantly, powered by the fine-tuned Qwen3 model.
nanoclaw-mini
A minimal Claude-style AI agent built from scratch — agent loop, tool use, and LLM orchestration in a nano footprint.
churn_pipeline
End-to-end customer-churn ML pipeline — data prep, training, artifacts, and one-command service scripts.
threat_indicator_analyzer
LLM-powered conversational app for analyzing security threat indicators.
Practical-NLP
Practical NLP in code — pipelines, text representation, classification, information extraction, and real case studies.
Redis-For-AI
Redis in the AI stack — semantic search, vector search, Redis as a vector DB, RedisVL, and hands-on projects.
Skills & Tech Stack
Generative AI
LLM Frameworks
NLP
Backend Engineering
DevOps & Cloud
Databases
Certifications
15 verified credentials across GenAI, LLMs, RAG, RL, NLP, and enterprise architecture. Click any certificate to view it full-size.
Additional Credentials
06. What's Next?
Get In Touch
I'm open to GenAI consulting, LLM architecture discussions, and enterprise AI collaborations. Whether you have a question or just want to say hi, my inbox is always open — I'll do my best to get back to you!