yashwadgave!

Yash@MacBook — Terminal

██╗   ██╗ █████╗ ███████╗██╗  ██╗
╚██╗ ██╔╝██╔══██╗██╔════╝██║  ██║
 ╚████╔╝ ███████║███████╗███████║
  ╚██╔╝  ██╔══██║╚════██║██╔══██║
   ██║   ██║  ██║███████║██║  ██║
   ╚═╝   ╚═╝  ╚═╝╚══════╝╚═╝  ╚═╝

██╗    ██╗ █████╗ ██████╗  ██████╗  █████╗ ██╗   ██╗███████╗
██║    ██║██╔══██╗██╔══██╗██╔════╝ ██╔══██╗██║   ██║██╔════╝
██║ █╗ ██║███████║██║  ██║██║  ███╗███████║██║   ██║█████╗  
██║███╗██║██╔══██║██║  ██║██║   ██║██╔══██║╚██╗ ██╔╝██╔══╝  
╚███╔███╔╝██║  ██║██████╔╝╚██████╔╝██║  ██║ ╚████╔╝ ███████╗
 ╚══╝╚══╝ ╚╝  ╚╝╚═════╝  ╚═════╝ ╚╝  ╚╝  ╚═══╝  ╚══════╝

I love working through messy systems/workflows and stick with them until they work in prod!

loading work_history...

✱AI Engineer @ Square Yards

Nov 2025 — Present • Mumbai

-Built MCP servers used as shared infrastructure across internal AI apps and external ChatGPT app SDK workflows.

-Built a real-estate AI assistant with persistent memory and dynamic context, backed by a custom MCP server.

-Built a search suggestion service from Matomo clickstream data, deriving city/entity/intent vocabulary and serving typed-prefix suggestions through FastAPI.

stack:

LLMsPrompt EngineeringRe-ranking SystemFastAPI Server

✱Founder/CTO @ Tisac AI Technologies

May 2023 — Oct 2024 • Hybrid

-Built enterprise AI tools for data labeling, model training/deployment, and Slack-based customer support workflows.

stack:

PythonDockerAWSLangChainLLMs

✱Data Science Intern @ TruBoard Partners

Jan 2022 — Jun 2022 • Mumbai

-Built solar power prediction models and loan-document extraction workflows using Python, scikit-learn, and Azure OCR.

stack:

Scikit-LearnAzureOCRData Engineering

loading selected_projects...

AI Agent Runtime Audit and Governance SDK(AI/Compliance • Python, Poetry)

Built a Python SDK for auditing and governing AI agent runtimes by capturing execution events, enforcing policies and guardrails, redacting sensitive data, and generating tamper-evident evidence packs with hash-linked integrity for compliance review and operational oversight. Open-sourced it with Apache-2.0 license.

PythonPoetryGuardrailsComplianceAudit Trails

Memory-engine(AI/Memory • Python, SQLite (local storage))

Built an experimental memory framework for LLM agents to store, retrieve, decay, and reason over long-term memories using SQLite-backed local storage. Added cleanup logic that can rewrite, invalidate, and remove stale memories to keep context useful and redundancy-free.

PythonSQLiteAI MemoryLLM Agents

Agentic Coding Tool(DevTools/Agents • Python, asyncio, Docker SDK)

Built a Python coding assistant with sandboxed shell execution, file tools, streaming OpenAI responses, persistent sessions, and path validation for safer agent workflows.

PythonasyncioDocker SDKOpenAI APIpytestRich

Operating System Language Model(AI/Systems • Python, PyTorch, Typer)

Built a custom OS-focused language model in PyTorch for command-aware assistance, with a guarded training pipeline, tokenizer, CLI, and FastAPI runtime.

PythonPyTorchTyperHySSMoEFastAPI

AI Code Reviewer Platform(DevTools • Python)

Full-stack platform for AI-powered PR reviews and SAST scans. Reduced review time by 40% and bugs by 50%.

PythonGitHub APIOpenAIAWSNextJS

Slack Customer Support Platform(Enterprise • Python)

Built an AI support platform that turns Slack conversations into tracked issues and resolution dashboards.

PythonSlack APIOpenAIAzure

AI Development Platform(MLOps • Azure AI Foundry)

Built a platform for training and deploying LLMs across cloud and on-prem infrastructure.

Azure AI FoundryDockerNodeJS

RAG(AI/ML • Python)

Built a RAG pipeline with FAISS and HNSW for fast vector search and retrieval-augmented generation.

Pythonllamaindexfaiss-cpu

Composio MCP Tools(Agents • Python)

Built Mail, Calendar, and GitHub agents with LangChain and Composio MCP, using OAuth-secured integrations.

PythonLangChainComposio MCP

Kafka Lab(Data/Streaming • Python)

Built a local Kafka lab with Docker, Python producers/consumers, and a stream processor to demonstrate partitions, consumer groups, offsets, lag, and at-least-once processing.

PythonDockerApache Kafka

compiling certifications...

✓[CREDENTIAL] Analyze Datasets and Train ML Models using AutoMLVERIFIED

source:Coursera

verify:[BZ75BTL4VD9Z]

✓[CREDENTIAL] Build, Train, and Deploy ML Pipelines using BERTVERIFIED

source:Coursera

verify:[3STZG4V889HW]

✓[CREDENTIAL] Optimize ML Models and Deploy Human-in-the-Loop PipelinesVERIFIED

source:Coursera

verify:[LYMJFK9LAKMG]

✓[CREDENTIAL] Practical Data Science on the AWS CloudVERIFIED