Open to Work: AI/ML Engineer

01 // Introduction

Aaryan Kurade

Machine Learning Engineer

02 // Profile

About Me

I am an AI/ML Engineer specialized in architecting high-performance Computer Vision systems and Agentic AI workflows. Expert in building autonomous systems using LangGraph and Agentic RAG, while optimizing vision models via ONNX for real-time inference. Proven track record in deploying scalable, non-blocking backends using FastAPI and Docker, with a focus on system observability and hardware-efficient execution.

03 // Stack

Technical Arsenal

Languages & Core

  • Python
  • MySQL

Computer Vision

  • PyTorch, TensorFlow
  • YOLO, RF-DETR, CNNs, ONNX
  • OpenCV, OCR
  • VLMs, 3D Vision
  • Object Detection, Segmentation, Classification, Keypoint Detection

AI Agents & LLMs

  • LangChain, LangGraph
  • Agentic RAG
  • Hugging Face Transformers
  • Vector DBs (Pinecone/Chroma)
  • vLLM, LoRA / PEFT, Mixed-precision (AMP)

MLOps & Backend

  • Docker, FastAPI
  • Linux
  • Git & CI/CD
  • Prometheus, Streamlit
  • Quantization (INT8/INT4) & Pruning

04 // Portfolio

Featured Projects

AI Visual Search Engine

Deployed semantic search for 100K fashion images using CLIP embeddings + FAISS. Optimized for production with GPU acceleration and hardware detection.

< 100ms P95 Latency
60%+ Memory Efficiency
99%+ Uptime
Pytorch CLIP FAISS Docker

Video Anomaly Detection

Non-blocking video processing pipeline using Convolutional Autoencoders. Engineered to handle high-bitrate streams without timeout errors.

0.92 Precision
Non-blocking Async
Prometheus Monitoring
PyTorch Autoencoder MLOps

Deepfake Detection

Real-time binary classifier using EfficientNet-B0 and MTCNN. Features a scalable REST API and a comprehensive ethics report on responsible AI deployment.

91.2% Accuracy
0.978 ROC-AUC
Grad-CAM XAI
PyTorch FastAPI Docker XAI

05 // Career

Experience

Machine Learning Engineer - Intern

Utopia Optovision Pvt. Ltd.
Jan 2024 - Jan 2025
  • Deployed YOLO + OCR pipeline for automated document text extraction, processing 2,000+ invoices daily.
  • Reduced OCR error rate from 18% to 7% through image preprocessing (deskewing, contrast normalization).
  • Applied advanced computer vision approaches by leveraging OCR and object detection, resulting in a 15% improvement in model accuracy for a key product feature.

Software Engineer - Intern

Arakoo.ai
Aug 2025 - Nov 2025
  • Built real-time ASR pipeline with Voice Activity Detection, reducing false transcription triggers by 40% via signal preprocessing.
  • Deployed speaker diarization module using FastAPI async endpoints handling 50+ concurrent audio streams.
  • Implemented prompt caching strategies cutting LLM inference costs by $0.02/minute of audio processed.

06 // Background

Education

MIT World Peace University

B.Tech, Electronics & Communication Engineering - AI/ML

Jun 2021 - Jun 2025

Pune, India