class YashChindam:
def __init__(self):
self.name = "Yash Chindam"
self.role = "AI / ML Engineer"
self.focus = ["LLMs", "RAG Systems", "Computer Vision", "NLP", "Deep Learning"]
self.passion = "Building AI systems that solve real-world problems"
self.currently = "Exploring Generative AI & multimodal research"
self.hf_profile = "https://huggingface.co/yashchindam"
def say_hi(self):
print("Thanks for dropping by! Let's build something intelligent together 🚀")
me = YashChindam()
me.say_hi()
7 PRs merged · 1 bundled extension shipped inside Spec Kit · 2 packages in its community catalog
github/spec-kit — GitHub's Spec-Driven Development toolkit
| Merged | What it was |
|---|---|
#4488 |
Bundled github extension for taskstoissues — ships inside Spec Kit's own catalog. Task resolver ported across Bash, PowerShell and Python. 2,455 lines / 13 files / 24 review rounds, 1,422 of them tests. Built another user's feature request (#4421). |
#4250 |
Preset-to-extension dependencies. Installing a preset without its companion silently did nothing. Added requires.extensions with PEP 440 validation and an install-time check naming the exact remediation for five failure states. |
#4424 · #4397 · #4396 |
Three fixes — reference docs that had drifted from the shipped workflow (plus a test that fails on future drift), one JSON key meaning two different paths across three language ports, and template composition looping forever on a literal token. |
Community catalog · speckit-inventory (extension) and inventory-alignment (preset) — published and maintained at v0.1.1, source at spec-kit-inventory-alignment.
mlflow/mlflow — the open-source AI engineering platform (~22k ★)
| Merged | What it was |
|---|---|
#25556 |
LLM-as-a-judge scoring failed on every Vertex AI Claude model — the gateway's adapter_class path bypassed the provider's own _prepare_payload(), so Vertex request fields were never applied. Diagnosed it, filed #25543, fixed it with a regression test. |
#25795 |
Bedrock Titan and AI21 adapters silently dropped top_p — set by the caller, never sent, no error raised. Reported as #25571, then mapped it onto each adapter's native field name. 22 lines of fix, 104 of test. |
Security model: Rego policy-as-code that fails closed · Keycloak OIDC with an asymmetric algorithm allowlist · capability registry whose discovery reveals only what the caller may see · tenant-isolated jobs and evidence
Stack: |
Engineering: three separately reported CI layers (unit/static, integration, Playwright) gate the release image · CD publishes a versioned OCI artifact · production startup refuses the dev key
Stack: |
Self-optimizing: an evaluator scores retrieval recall, grounding and forbidden claims deterministically rather than by LLM judgment, then a control loop perturbs one pipeline field at a time within reviewer-approved bounds and keeps only Pareto-optimal candidates that never regress authorization, latency or quality
Stack: |
Adversarial evaluation: a PyRIT-style red-team suite covering direct and indirect injection, multi-turn jailbreak, encoded instructions, cross-tenant access, tool privilege escalation and MCP tool poisoning — scored against a committed baseline so a regression fails CI instead of landing silently
Stack: |
Results: RMSE
|
Throughput: 9-step automated pipeline · parallel processing across up to 4 API keys via |
🗂️ More Projects (click to expand)
| Project | Description | Stack |
|---|---|---|
| Intelligent Claims Document Processing | ClaimLens AI — agentic pipeline for US commercial property insurance across 8+ document types | LangGraph Azure OpenAI Pydantic |
| AI-Powered Natural Language to SQL Engine | NaturalSQL — plain English to executable PostgreSQL via SQLCoder-7b-2 | SQLCoder-7b-2 PyTorch Cloud SQL |
| AI Voice Onboarding System | Modular AI onboarding framework with multi-LLM support and guided setup workflows | LangChain LlamaIndex FastAPI |
| RFP Document Info Extraction via LLMs | Structured extraction from RFP documents, 85–92% accuracy at 30–60s/doc | GPT-4 LangChain PyPDF2 |
| Vision-Based Entity Extraction | OCR + NER over forms, invoices, ID cards and business cards — entity F1 80–92% | EasyOCR spaCy YOLO |
| Multi-PDF Chatbot with RAG & FAISS | Chat across many PDFs at once with RAG over FAISS | Mistral Nemo FAISS LangChain |
| ECO2 — Environmental ML Platform | Carbon footprint tracking, climate modeling and biodiversity assessment | GeoPandas NetCDF4 Plotly |
| YouTube Video Summarizer | Transcribes and summarizes YouTube videos with a Streamlit UI | Gemini Pro Streamlit |
| RAG w/ LLaMA2 + LangChain + ChromaDB | End-to-end RAG pipeline using LLaMA 2 | LLaMA 2 ChromaDB |
| PDF Chatbot with RAG | Conversational PDF Q&A with RAG architecture | RAG FAISS LLMs |
| Image Captioning | Deep learning-based automatic image captioning | PyTorch CNN LSTM |
| License Plate Recognition | Automatic license plate detection and OCR | OpenCV OCR |
| Text Summarization — BART | Abstractive text summarization with BART | BART Transformers |
| Research Paper Title Generator — BART | Fine-tuned BART for academic title generation | BART Transformers |
| Movie Title Generator — Flan-T5 | Flan-T5 fine-tuned for cinematic title generation | Flan-T5 HuggingFace |
| Predicting Credit Card Approvals | ML classifier for credit card approval prediction | scikit-learn Pandas |
| RAG Implementation & Prompt Optimization | Benchmarking and optimizing RAG prompt strategies | RAG LLMs |
Languages
Agents & LLM Orchestration
Retrieval & Knowledge
Serving & Infrastructure
MLOps, Evaluation & Testing
Cloud & Deep Learning
Published models & datasets on Hugging Face
| Resource | Link |
|---|---|
| 🧬 Drug-Protein Interaction Model | yashchindam/Drug-Protein-Interaction-Prediction-Using-CLIP-and-Deep-Learning |
| 📦 Drug-Protein Dataset | datasets/yashchindam/Drug-Protein-Interaction-Prediction-Using-CLIP-and-Deep-Learning |
"The best way to predict the future is to invent it." — Alan Kay