I build practical AI/ML systems with a focus on multilingual speech AI, large language models, retrieval-augmented generation, and AI applications for digital payments.
My work combines hands-on experience in the digital payments ecosystem with a strong interest in building and evaluating AI systems for real-world applications, particularly for Indian languages and financial use cases.
- 🤖 Machine Learning
- 🗣️ Speech AI & Automatic Speech Recognition (ASR)
- 🌐 Multilingual AI for Indian Languages
- 🧠 Large Language Models (LLMs)
- 🔎 Retrieval-Augmented Generation (RAG)
- 🛠️ LLM Fine-Tuning & QLoRA
- 💳 AI for Digital Payment Systems
- 📊 Model Evaluation & Benchmarking
- 🚀 AI Inference & Model Serving
Benchmarking AI4Bharat IndicConformer-600M for multilingual Automatic Speech Recognition across 9 Indian languages and 900 audio samples.
Highlights:
- 9 Indian languages
- 900 audio samples
- Word Error Rate (WER) evaluation
- IndicConformer-600M
- RNNT decoding
- CPU vs GPU inference benchmarking
A Retrieval-Augmented Generation system for answering questions from RBI regulatory documents.
Highlights:
- PDF document processing
- Semantic chunking experiments
- Sentence Transformers embeddings
- ChromaDB vector search
- Local LLM inference with Ollama
- Retrieval evaluation using Recall@1, Recall@5 and MRR
Fine-tuning Microsoft Phi-3 Mini 3.8B for payment-related intent classification.
Highlights:
- Phi-3 Mini 3.8B
- 7 payment intents
- QLoRA
- 4-bit quantization
- Parameter-efficient fine-tuning
- Baseline vs fine-tuned evaluation
- Python
- SQL
- PyTorch
- Hugging Face Transformers
- Sentence Transformers
- LLMs
- RAG
- Fine-Tuning
- QLoRA
- ChromaDB
- Ollama
- Docker
- Git
I am particularly interested in building AI systems that move beyond experimentation into reproducible, measurable and production-oriented solutions.
Current areas of focus include:
- Multilingual Speech AI
- LLM applications
- Retrieval systems
- Efficient LLM fine-tuning
- Model evaluation and benchmarking
- AI inference and model serving
⭐ Feel free to explore my repositories to see the experiments, implementations and evaluation behind these projects.