Prasanna
Patil, AI Engineer · Backend + Computer Vision · Pune, India
I build production AI systems in Python — computer vision pipelines, backend APIs, automation workflows, and LLM-powered tools.
02intro
About
- Based inPune, Maharashtra, India
- CurrentlyAI Engineer @ Zuneko Labs
- EducationB.Tech AI & Data Science, 2026
- FocusBackend, Computer Vision, AI Automation
- BuildingProduction AI systems with Python
I write Python for production AI systems — backend APIs, async workers, computer vision pipelines, database design, and LLM-powered automation. At Zuneko Labs, I work across CCTV/video intelligence, WhatsApp automation, document ingestion, and reliability workflows that run beyond demos.
services
What I can build for you
Open to full-time roles and to freelance or consulting work, with teams in India and remotely. How that works.
AI backend engineering
I build the backend around AI features — the API, the queue, the database and the failure handling — so a model that works in a notebook keeps working when real users and real traffic hit it.
Explore ai backend engineeringComputer vision
I build video pipelines that turn camera feeds into events someone can act on — who or what was detected, where, and when — and that keep up in real time on the hardware you actually have.
Explore computer visionLLM & WhatsApp automation
I connect language models to the channels your customers already use — mostly WhatsApp — and build the plumbing that keeps those conversations and documents from getting lost.
Explore llm & whatsapp automation
03stack
Technical Stack
What I reach for without thinking.
Python, FastAPI, Pydantic, SQLAlchemy, PostgreSQL, Redis, Celery, Docker, Git/GitHub, Linux/Bash, Postman, pytest — for REST APIs, async workers, schema migrations, and production workflows.
Used on real systems.
Django, Flask, React, MongoDB, Supabase, OpenCV, YOLO, DeepSORT/ByteTrack, ONNX, TensorRT, NVIDIA Jetson, TensorFlow, PyTorch, CNN/LSTM, Librosa, PyAudio, LLaMA/OpenAI APIs, LangChain, RAG pipelines, FAISS, Pinecone, Meta WhatsApp Business API, Twilio, Webhooks, WebSockets, Nginx, GitHub Actions. Used across backend services, CCTV/video intelligence, speech emotion recognition, WhatsApp automation, and AI workflow reliability.
Currently picking up.
MLOps tooling, gRPC, Kubernetes basics, AWS/GCP beyond the fundamentals, and Rust. The goal is stronger production AI systems: better retrieval, deployment, observability, and service boundaries.
04work
Selected Work
Speech Emotion Recognition (SER)
Speech Emotion Recognition system using CNN, LSTM, and CLSTM. Trained on CREMA-D, RAVDESS, TESS, and SAVEE — 93.27% accuracy. Real-time inference pipeline for live audio with a Django REST backend and React frontend, aimed at customer service and healthcare use cases.
CCTV Analytics for Crime & Crowd Management
End-to-end surveillance platform for public safety. Crowd density estimation, crime detection, facial recognition. MongoDB for event persistence, Twilio and WhatsApp for real-time alerts. Presented at Smart India Hackathon 2023.
Agentic Honey-Pot — AI Counter-Scam Platform
Built at GUVI AI Impact Buildathon 2026. LLM-driven personas engage live scammers in real time to stall them and extract threat intelligence. FastAPI orchestration with persona/strategy switching and semantic scam-probability scoring; React 19 + Vite dashboard with API-key auth and rate limiting.
WhatsApp Automation & AI Agent Platform
Backend for automated WhatsApp workflows — webhook ingestion, user state tracking, async AI responses, conversation history. Redis + Celery for reliability. Built for a client at Shivohini TechAI.
05career
Experience
Zuneko Labs by Emdee Digitronics
AI Engineer
- Own end-to-end development of production AI and backend systems: activity-based time tracking and billing, healthcare workflows, conversational/voice agents, document automation, and computer vision.
- Build Python APIs (FastAPI/Django), AI services, automation pipelines, and third-party integrations across databases, messaging platforms, cloud services, and real-time processing.
- Develop and maintain activity-based client billing, WhatsApp document workflows, AI voice agents, and ANPR/CCTV analytics, with a focus on reliability and deployment.
- Hardening internship-era pipelines into monitored, recoverable production services.
Zuneko Labs by Emdee Digitronics
Computer Vision Intern
- Built a real-time person detection and tracking pipeline on CCTV feeds using frame-by-frame detection and multi-frame tracking.
- Built a WhatsApp-based document ingestion system using the WhatsApp Business API to pull media from group chats and upload it to Google Drive.
- Wrote a recovery mechanism to backfill missed files after downtime or network failures.
Shivohini TechAI LLP
AI/ML Intern (Backend-Focused)
- Built backend for conversational AI agents using LLaMA and OpenAI APIs. Focused on keeping context across turns without blowing token budgets.
- Built WhatsApp automation for clients — webhook ingestion, message routing, template management via Meta Business API.
- Moved message processing, AI inference, and DB writes off the request thread with Redis and Celery.
- Migrated client databases from MySQL to Supabase/PostgreSQL mid-project. Kept the AI agents running throughout.
- Talked directly to clients to figure out what they actually needed, not just what they asked for.
Smart India Hackathon (Government of India)
Finalist - Backend & CV
- Built a CCTV analytics backend for crime detection and crowd monitoring. Presented to a government panel.
- CV pipeline in OpenCV: facial recognition, crowd counting, anomaly detection.
- APIs + background workers for real-time video analysis and alert dispatch.
- Twilio and WhatsApp integration for instant incident notifications.
background
Education
B.Tech in Artificial Intelligence & Data Science
Dr. D. Y. Patil School of Science & Technology, Pune
credentials
Certifications
Oracle Cloud Infrastructure 2025 Certified Generative AI Professional
Oracle University
Machine Learning & Data Science Using Python
Infosys Springboard
IgniteX Program Participant
Wadhwani Foundation
Smart India Hackathon Finalist
Government of India
06get in touch
Contact
Let's build something
that survives production.
Currently an AI Engineer at Zuneko Labs. Open to full-time AI/backend engineering roles and to freelance or consulting work — see how that works.
Say helloOr pick a slot directly
explore
Work with me, or read how I work
Hire by technology
- Freelance fastapi developer
- Freelance yolov8 developer
- Freelance langchain developer
- Freelance celery developer
- Freelance redis developer
- Freelance opencv developer
Engineering guides
- FastAPI, Celery and Redis: A Production Architecture Guide
- Building Real-Time CCTV Analytics with YOLO
- Webhook Idempotency in FastAPI: Never Process an Event Twice
- Running YOLO on a Jetson: ONNX and TensorRT in Practice
- Celery Task Recovery: What Happens When Things Break
- A RAG Evaluation Checklist Before You Promise Accuracy