2025
Agentic AI Playground
Modular AI agents using Dify, LangChain, and CrewAI for multi-step reasoning and workflow automation. Integrated observability, vector search, and dynamic tool orchestration.
LangChain · CrewAI · Dify · Multi-Agent
SENIOR SOFTWARE ENGINEER · AI RESEARCHER
Ramin Sharifi builds intelligent systems that move from research to production. Transforming cutting-edge AI concepts into production-ready solutions at the intersection of ML, software engineering, and autonomous agents.
Toronto, Ontario, Canada
Senior Software Engineer / Team Lead @ Turing
01 / SELECTED WORK
AI agents · telemetry · computer vision · forecasting
Systems Built
2025
Modular AI agents using Dify, LangChain, and CrewAI for multi-step reasoning and workflow automation. Integrated observability, vector search, and dynamic tool orchestration.
LangChain · CrewAI · Dify · Multi-Agent
2025
Reusable agent pipelines for software engineering automation — code refactoring, repository organization, and documentation synthesis.
LangChain · CrewAI · Automation
2023
End-to-end pipeline for processing high-frequency sensor streams with live visualization of time-series data, anomaly detection alerts, and predictive analytics.
AWS · Kafka · React · Time-Series
2021
Mobile-optimized computer vision system for medical image classification. Separated detection and classification phases for improved accuracy with on-device inference via CoreML.
Swift · CoreML · Computer Vision
2019
LSTM-based forecasting model for mobile user-activity prediction. Published at IEEE PACRIM 2019 — demonstrates sequential pattern analysis for real-world mobile data.
LSTM · PyTorch · IEEE
02 / EXPERIENCE
Years in ML/AI
Jan 2025 — Present
Palo Alto, CA (Remote)
• Delivery manager and team lead for Google's EDU TerminalBench and Google's Apps Script Bench • Awarded Turing Google Hero of the Month for outstanding contributions • Designed real-time data processing pipelines for anomaly detection and forecasting in large-scale autonomous systems • Built scalable backend services using FastAPI, Celery, and PostgreSQL for high-frequency data ingestion • Architected multi-agent AI systems integrating predictive signals and cross-agent coordination • Developed full-stack dashboards in React.js/Next.js for visualizing time-series telemetry and live metrics • Led cross-functional engineering efforts integrating ML-powered analytics into production systems
Jan 2023 — Aug 2023
Victoria, BC
• Built end-to-end IoT data pipelines for high-frequency sensor streams using AWS/GCP • Designed ML models for sequential pattern analysis, forecasting, and anomaly detection • Optimized ML inference pipelines for near-real-time operation
Nov 2021 — Dec 2022
Victoria, BC
• Utilized YOLO V7 for object detection with automated annotation workflows • Integrated Hidden Markov Models into ML pipelines for sequential data analysis • Applied data mining techniques for business intelligence at scale
Apr 2019 — Nov 2021
Victoria, BC
• Conducted research in capsule networks for image classification and object detection • Optimized models using pruning techniques, reducing computational costs
Sep 2020 — Oct 2021
Victoria, BC
• Developed iOS apps with on-device ML inference using Swift and CoreML • Designed the Gelderm classifier for improved medical image classification
03 / CAPABILITIES
Python · Swift · C++ · Java · TypeScript
PyTorch · TensorFlow · Scikit-Learn · LangChain · CrewAI
AWS · GCP · Docker · Kafka · PostgreSQL
FastAPI · React / Next.js · Django / Flask · Celery · MongoDB
LLMs (GPT / Claude / Gemini) · Computer Vision · Time-Series / IoT · Agentic Systems · Object Detection (YOLO)
04 / RESEARCH
Publications
R. Sharifi, P. Shiri, A. Baniasadi
IEEE ICMLA 2021
Co-Author
P. Shiri, R. Sharifi, A. Baniasadi
IEEE/ACS AICCSA 2020
Co-Author
R. Sharifi, P. Shiri, A. Baniasadi
CATA 2020
First Author
R. Sharifi, M. M. Majdabadi, V. Tabataba Vakili
IEEE PACRIM 2019
First Author
05 / ABOUT

Senior Software Engineer with deep expertise in time-series modeling, IoT data pipelines, and applied deep learning. I specialize in transforming complex AI research into production-grade systems that operate at scale.
My work spans sequential prediction using LSTM/GRU architectures, anomaly detection for sensor-driven systems, and large-scale data engineering pipelines deployed on cloud platforms. I’ve published in IEEE conferences and led teams building multi-agent AI systems.
MASc, University of Victoria
University of Victoria · Electrical & Computer Engineering
2021
BSc, Iran University of Science and Technology
Iran University of Science and Technology · Electrical Engineering
2018
06 / SECURE CONTACT
Use the public key below to verify identity and encrypt sensitive correspondence. Always compare the fingerprint through a separate trusted channel.
HOW TO FETCH IT
Keyserver
Convenient, but verify the fingerprint above through a separate trusted channel before you rely on the key.
gpg --recv-keys 71BFB22FC742C32CBCE7EA41D825C517F3A677D9
gpg --search-keys raminsharifi@proton.me
Direct download
Import the armored public key straight from this site.
curl -s https://raminsharifi.ca/ramin.sharifi.asc | gpg --import -
07 / LATEST WRITING
2026-04-21
12 min read
A field report on the bugs I hit while shipping TimeLogger across iOS, macOS, watchOS, and widgets — silent BLE back-pressure, timestamp comparisons that lie, Live Activities that outlive your process, and a handful of other footguns.
Swift · iOS · macOS · watchOS · Debugging · BLE · CloudKit · Side Project
2026-04-16
10 min read
How I built a multi-device time tracker with a single Rust server as the brain and native Swift clients for iOS, macOS, and watchOS — syncing over Wi-Fi, BLE, and iCloud.
Rust · Swift · iOS · watchOS · Side Project · SQLite
2026-03-20
8 min read
A tour of the command-line tools I rely on daily as an ML engineer — from terminal multiplexing to fuzzy finding — and how I use Restic to keep bulletproof backups of everything that matters.
CLI · Tooling · Backup · DevOps · Productivity