AI/ML Engineer · Generative AI · LLM & Agentic Systems
Building production-grade AI systems with LLMs, RAG, agentic workflows, and machine learning.
I am an AI/ML Engineer specializing in Generative AI, Large Language Models, Agentic Systems, and Retrieval-Augmented Generation (RAG). My focus is translating research-stage AI into reliable, production-ready software — spanning model pipelines, backend APIs, vector stores, and end-to-end deployment.
🎓 B.Sc. (Hons) Artificial Intelligence & Machine Learning · 2026
| Domain | Focus |
|---|---|
| Generative AI | LLMs, prompt engineering, embeddings, vector search |
| Agentic Systems | Multi-agent orchestration, tool calling, LLM reasoning |
| RAG | Retrieval pipelines, knowledge grounding, hybrid search |
| Local AI | On-device inference, GGUF models, Ollama |
| Model Development | Fine-tuning, evaluation, multilingual adaptation |
| Deep Learning | Computer vision, neural architectures, PyTorch / TensorFlow |
|
Privacy-focused local AI assistant for text and image interactions. Built on local LLM inference with agentic workflow support and full offline capability. 
|
AI-powered scheduling system that automates timetable generation while resolving complex constraints and conflicts.
|
|
Fine-tuning and adaptation of Google's Gemma model for the Marathi language. Explores multilingual model adaptation and low-resource language processing.
|
Research and implementation of architectures combining retrieval, reasoning, tool use, and multi-step task execution using LangChain and LangGraph. 
|
AI & Machine Learning
Generative AI & LLMs
Backend
Databases & Vector Stores
Frontend
Tools & Infrastructure
Data ──► Models & LLMs ──► Retrieval & Knowledge
│
Deployment ◄── Applications ◄── Agents & Tools ◄── Backend APIs
Building AI systems that are not just accurate in benchmarks, but reliable and useful in production.
- Agentic RAG architectures and evaluation frameworks
- LangGraph-based multi-agent orchestration
- Long-term memory and context management for AI systems
- Multilingual LLM adaptation
- AI infrastructure, observability, and deployment at scale