Skip to content
View Mohanaspiringcoder's full-sized avatar
πŸ’­
Machine Learning | Multilingual Speech AI | ASR | NLP | Python | NVIDIA Triton
πŸ’­
Machine Learning | Multilingual Speech AI | ASR | NLP | Python | NVIDIA Triton

Block or report Mohanaspiringcoder

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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
Mohanaspiringcoder/README.md

Hi πŸ‘‹, I'm Mohan

Applied AI / ML Engineer | Agentic AI | LLMs | RAG | Speech AI

I build practical AI/ML systems with a focus on Agentic AI, large language models, retrieval-augmented generation, multilingual speech AI, and AI applications for digital payments.

My work combines hands-on experience in the digital payments ecosystem with building and evaluating AI systems for real-world applications, particularly across financial use cases, Indian languages, and intelligent automation.


🧠 Core Areas

  • πŸ€– Agentic AI & LLM Orchestration
  • 🧠 Large Language Models (LLMs)
  • πŸ”Ž Retrieval-Augmented Generation (RAG)
  • πŸ› οΈ LLM Fine-Tuning & QLoRA
  • πŸ—£οΈ Speech AI & Automatic Speech Recognition (ASR)
  • 🌐 Multilingual AI for Indian Languages
  • πŸ”— Tool Calling & AI Workflow Automation
  • πŸ›‘οΈ AI Guardrails & Groundedness
  • πŸ“Š Model Evaluation & Benchmarking
  • πŸš€ AI Inference & Model Serving
  • πŸ’³ AI for Digital Payment Systems

πŸš€ Featured Projects

An agentic AI system for UPI payment operations and failure investigation, combining structured transaction analytics, operational RAG, grounded reasoning, validation/retry workflows, human-in-the-loop approval, and simulated incident management.

Highlights:

  • LangGraph-based agent orchestration
  • Planner and intent-based workflow routing
  • SQLite-based payment transaction analytics
  • Operational RAG using ChromaDB and Sentence Transformers
  • Local LLM inference with Ollama
  • Evidence-grounded investigation generation
  • Guardrails for unsupported numeric and causal claims
  • Validation and retry workflow
  • Human-in-the-loop approval before incident creation
  • Simulated incident management
  • MCP server exposing operational tools
  • Automated evaluation framework
  • 37 automated tests
  • Synthetic evaluation datasets for intent, retrieval, groundedness, task completion, and recovery

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 using semantic retrieval and local LLM inference.

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

πŸ› οΈ Technical Stack

Languages

  • Python
  • SQL

Machine Learning & AI

  • PyTorch
  • Hugging Face Transformers
  • Sentence Transformers
  • Large Language Models
  • RAG
  • Fine-Tuning
  • QLoRA

Agentic AI

  • LangGraph
  • LangChain
  • Tool Calling
  • Agent Workflows
  • AI Guardrails
  • Human-in-the-Loop
  • MCP

AI / ML Infrastructure

  • ChromaDB
  • SQLite
  • Ollama
  • Docker
  • Git
  • Linux

πŸ“Š Engineering Focus

I am particularly interested in building AI systems that move beyond experimentation into reproducible, measurable, and production-oriented solutions.

My current areas of focus include:

  • Agentic AI systems
  • LLM applications
  • Retrieval systems
  • Efficient LLM fine-tuning
  • Multilingual Speech AI
  • AI evaluation and benchmarking
  • Grounded generation and guardrails
  • AI inference and model serving
  • AI applications for digital payments

πŸ“« Contact

πŸ“§ mohandongara@gmail.com


⭐ Feel free to explore my repositories to see the implementations, experiments, evaluations, and engineering decisions behind these projects.

Pinned Loading

  1. indicconformer-asr-benchmark indicconformer-asr-benchmark Public

    Benchmarking AI4Bharat IndicConformer ASR across major Indian languages using the Kathbath dataset and Word Error Rate (WER).

    Jupyter Notebook 1

  2. finrag-rbi-document-qa finrag-rbi-document-qa Public

    A local RAG-based question answering system for RBI documents using ChromaDB, Sentence Transformers, and Llama 3.2 running with Ollama.

    Python

  3. phi3-payment-intent-finetuning phi3-payment-intent-finetuning Public

    Fine-tuning Phi-3 Mini for payment intent classification using QLoRA.

    Jupyter Notebook

  4. payops-agent payops-agent Public

    Agentic AI copilot for UPI payment operations, failure investigation, RAG-based operational knowledge, grounded analysis, and human-approved incident management.

    Python