Hi, I'm

Pranav Krishna
Danda

Software Engineer

Building production AI systems — autonomous agents, backend infrastructure, and LLM pipelines at scale.

Scroll
Currently Building → Scaled Autonomous Agentic Systems

Software Engineer with 1+ year of production experience building autonomous AI agents, backend systems, and LLM pipelines.

Currently at Oovacha, automating clinical data workflows across 27 trial sites. Previously at Mushroom Solutions building deep learning classification systems.

Based in Hyderabad, India. B.Tech in Computer Science & Engineering (AI & ML) from VVIT.

Open to full-time roles
0 AI Agents Shipped In production
78.6K + Records Processed Clinical data
0 hrs/week Time Automated Manual work eliminated
97.8 % Model Accuracy Peak classification

Software Developer

Oovacha

Mar 2025 — Present
  • Built 3 autonomous AI agent systems from scratch — an inline clinical query agent, an EDC validation engine, and a Claude-powered multi-tool framework — now live across 27 clinical trial sites
  • Designed and shipped a message-driven validation pipeline processing 78.6K+ clinical records against 77 configurable rules, catching discrepancies before human reviewers ever see them
  • Selected SQS over direct API calls to guarantee message durability and decouple processing load from clinical data ingestion
  • Architected backend infrastructure across AWS ECS Fargate, Aurora PostgreSQL, SQS, S3, and Cognito
  • Integrated custom MCP servers into AI pipelines, enabling natural language querying of production clinical databases
PythonClaude APIMCPFastAPIAWSPostgreSQLSQS

ML Engineer Intern

Mushroom Solutions

Mar 2024 — Mar 2025
  • Trained deep learning classification models hitting 97.8% accuracy on 15,400+ records — automated 17 workflows, eliminating 22 hrs/week of manual processing
  • Built an intelligent RAG chatbot combining Azure AI Search + FAISS with Redis caching, serving 5,000 queries/day
  • Shipped Django REST APIs with role-based access control, serving ML inference across 4 internal teams
  • Covered agent tool execution and edge cases with end-to-end test automation using Behave BDD
TensorFlowKerasFAISSDjangoRedisAzure AI Search
Production

Clinical AI Agent Framework

3 autonomous agents with tool execution, error recovery, and MCP-based natural language querying of production PostgreSQL databases.

PythonClaude APIMCPFastAPI

Proprietary — no public repo

Production

EDC Validation Engine

Message-driven 3-stage pipeline processing 78.6K+ clinical records against 77 configurable rules. SQS-backed for message durability.

PythonSQSPostgreSQLAWS

Proprietary — no public repo

Production

RAG Search Platform

Hybrid vector + keyword search behind Django APIs. 5,000 queries/day, sub-second latency across 10,000+ document corpus with Redis caching.

FAISSAzure AI SearchRedisDjango

Proprietary — no public repo

AI & Agents

Python Claude API MCP Protocol Autonomous Agents FAISS Hugging Face Azure AI Search TensorFlow Keras

Backend & APIs

FastAPI REST APIs SQLAlchemy Django Flask

Cloud & Infrastructure

AWS ECS Fargate SQS Aurora PostgreSQL S3 Cognito Docker

Databases & Messaging

PostgreSQL Redis RabbitMQ

Frontend

TypeScript Next.js React

Testing

Behave BDD Test Automation

I'm documenting what I build — agent architectures, backend design decisions, and lessons from production AI systems.

Coming Soon

How I built a 3-stage clinical validation pipeline with SQS

Coming Soon

MCP Protocol: What it is and why it matters for AI agents

Coming Soon

RAG vs Fine-tuning: What I learned building both in production

I'm actively looking for full-time Software Engineer roles focused on AI systems and backend infrastructure. Open to roles across India and remote opportunities globally.

Response time: usually within 24 hours.

Available for full-time roles · Based in Hyderabad, India