# Ariel Feygin

> Senior AI Software Engineer Fullstack  

  github.com/AviFeygin

Location: New York City Metropolitan Area, United States
Profile: https://flows.cv/arielfeygin

AI Engineer with deep expertise in production-grade machine learning pipelines, serverless cloud architecture, and intelligent automation systems. Specialized in embedding-based classification, HDBSCAN clustering, and large language model (LLM) integration to drive high-accuracy, low-latency solutions across complex domains.

At the Laboratory of Advanced Biotechnologies for Health Assessment, I developed cutting-edge computer vision algorithms using gait and eye tracking to identify early-stage neurological disorders, applying deep learning and spatiotemporal modeling in real-world diagnostic settings.

In industry, I’ve led the design of scalable AI platforms processing 100K+ records with sub-second latency, leveraging tools like Python, AWS Lambda, MongoDB, and advanced unsupervised learning techniques. My work emphasizes compute-efficient architectures and embedding-rich representations to enable actionable, data-driven insights in operational workflows.

Passionate about building systems that bridge research and production, I combine academic rigor with engineering precision to deliver robust, scalable, and interpretable AI.

## Work Experience
### Senior Software Engineer AI Platform @ ConnectWise (post-acquisition) 2026 @ zofiQ
Jan 2026 – Present
ZofiQ acquired by Connectwise

### AI Software Engineer @ zofiQ
Jan 2024 – Jan 2026
Developed a remediation agent that reads ConnectWise tickets, links them to devices in a ConnectWise-compatible RMM, and plans safe script runs using GPT-5 via the OpenAI API on AWS Lambda with Python 3, integrating PostgreSQL, MongoDB, Redis, and AWS Secrets Manager for secure, low-touch operation.

Designed a 20-step microservice workflow for orchestration, device mapping, SOP compliance checks, and real-time script monitoring with intelligent retry logic and GPT-5 ticket closability analysis to auto-close resolved tickets and shrink time-to-resolution.

Built an AI agent for managed service providers that acts as an ongoing issue detector by grouping related tickets with HDBSCAN, NumPy, Pandas, and scikit-learn, helping teams spot emerging problems across customers.

Shipped an embedding-based classification service using cosine similarity and vector normalization to auto-assign new tickets to the right issue cluster in milliseconds, reducing manual triage and misrouting.

Created a natural language processing (NLP) ticket triage pipeline with a novel energy-based sanitization step that cleans and normalizes noisy tickets, improving downstream identification and automated fix suggestions.

Architected the production system on AWS with Lambda, SQS FIFO, EventBridge, API Gateway, Cognito, FastAPI, and MongoDB Atlas to support real-time ticket processing and cluster management.

Built a modular data engine with MongoDB aggregation pipelines, batch processing, and connection pooling so clustering and classification stay fast under high ticket volume.

Implemented a content filtering layer with fuzzy logic, regex, and rule-based checks to remove spam and low-quality tickets before they reach the agents.

Set up structured JSON logging, CloudWatch monitoring, CloudFormation infrastructure as code, S3 artifact storage, and CI/CD pipelines to support reliable deployments and production debugging.

### MSc Student @ Lassonde School of Engineering - York University
Jan 2023 – Jan 2026 | Toronto, Ontario, Canada
MSc. Candidate for Machine Learning and AI(CS) for Bioengineering group at York University


## Education
### Masters in Computer Science
Lassonde School of Engineering - York University
Jan 2023 – Jan 2024

### Specialized Honours In Computer Science in Computer Science
Lassonde School of Engineering - York University
Jan 2019 – Jan 2023


## Contact & Social
- LinkedIn: https://linkedin.com/in/ariel-feygin
- GitHub: https://github.com/AviFeygin

---
Source: https://flows.cv/arielfeygin
JSON Resume: https://flows.cv/arielfeygin/resume.json
Last updated: 2026-04-01