Aditi Bindal
Software Engineer | DevRel | AI
Work Experience
Software Engineer Intern
EvalAI (by CloudCV) • Georgia, USA (Remote)
- • Contributing under Google Summer of Code 2025.
- • Worked on UI/UX for EvalAI’s main dashboard.
- • Wrote test cases for modules to increase coverage.
- • Improved the UI/UX & content of Documentation site.
- • Working on RAG-based chat assistant for enhanced support.
Developer Relations Engineer
NodeShift • Abu Dhabi, UAE (Remote)
- • Managing Developer Relations & Technical content.
- • Coordinating with engineering to resolve user queries.
- • Showcasing platform capabilities through tutorials, videos, & example snippets.
Software Engineering Contributor
Satlok Ashram AI (Non-Profit) • New Delhi, India
- • Contributed in fine-tuning Voice cloning model for a specific reference voice.
- • Integrated for multilingual speech specifically for low resources Indic languages like Hindi, Punjabi, Bangla, etc. (Wav2Vec2, F5-TTS).
- • Designed RAG solution for QnA from holy books.
- • Working on fine-tuning LLM (Llama, Gemma) with large dataset for end-to-end multilingual & multimodal spiritual conversation (Hindi, English).
Software Engineer Intern
HCLTech • Noida, India
- • Got hands on training under senior developers to understand industry insights.
- • Resolved L1 bugs & client tickets related to production server, deployment, & Linux environments.
- • Represented the work of interns team to cross functional teams & management.
Projects
OpenSorus: AI Maintainer Agent for GitHub Issues
huggingface.co/spaces/OpenSorus
OpenSorus is an autonomous GitHub Issues Maintainer Agent that augments open-source triage by aligning developer queries with semantically searched & indexed codebase contexts. Leveraging retrieval-augmented generation with LlamaIndex and Mistral’s Codestral model, the agent crafts and posts real-time, context-aware replies directly on GitHub.
Demo Interface is built with Gradio, and can be integrated seamlessly via GitHub App. This project has been recognized with the Mistral AI Choice Award at Hugging Face’s global Gradio Agents & MCP Hackathon.
Attention Is All You Need: Transformers Implementation From Scratch
github.com/aditi-dsi/attention-is-all-you-need
A ground-up PyTorch implementation of the original Transformer architecture as proposed in the paper “Attention is All You Need”. This project dissects core components like multi-head self-attention, position-wise feedforward networks, and layer normalization, reconstructing them from first principles to offer deep transparency into the model’s mechanics.
The implementation is heavily inspired by Professor Dr. Arun Rajkumar’s lectures for the course Responsible & Safe AI Systems, and it serves both as an educational reference and a minimal baseline for understanding modern NLP architectures.
Dog Breed Classifier: Pretrained-CNN Image Classifier
github.com/aditi-dsi/DogBreedClassifier
A comparative image classification pipeline leveraging pre-trained convolutional neural networks (AlexNet, VGG, ResNet) to distinguish dog breeds with high accuracy across varied input scenarios. The system evaluates model robustness on both canonical pet datasets and real-world edge cases, enabling inference on custom user images through a lightweight batch script. Built to benchmark architectural performance in fine-grained visual recognition tasks.
This project was part of my hands-on lab work in the AI & ML Nanodegree Program, completed as a scholarship recipient of the AWS AI & ML Scholarship.
Blogs
A curated list of my most-read technical articles & tutorials.
A Step-by-Step Guide to Install DeepSeek-R1 Locally with Ollama, vLLM or Transformers
dev.to/nodeshiftcloud/deepseek-r1DeepSeek-R1 is making waves in the AI community as a powerful open-source reasoning model, offering advanced capabilities that...
How to Install & Run OpenManus Locally with Ollama – No API Keys Required
dev.to/nodeshiftcloud/openmanusOpenManus is an open-source alternative to the groundbreaking Manus AI agent, developed by the MetaGPT community. Manus itself is...
A Step-by-Step Guide to Install Gemma-3 Locally with Ollama or Transformers
dev.to/nodeshiftcloud/gemma3Gemma-3 is Google’s latest open-weight large language model (LLM), pushing the boundaries of AI with...
Build a Browser Use Agent with DeepSeek: A Step-by-Step Guide
dev.to/nodeshiftcloud/browser-use-agentThe intersection of AI with web automation introduces a novel concept known as Browser Use agents. This concept enables...
Build Your Own AI Agent in Minutes with Eliza: A Complete Guide
dev.to/nodeshiftcloud/aiagentBuilding your own AI agent has never been easier than the current...