meryemsakin/production-ml-engineer-v3
Model Description
A production-ready ML engineer model, fine-tuned on 3+ years of real-world experience. Specializes in LLM agents, computer vision, and end-to-end deployment pipelines.
Model Details
| Model Type | Multi-task ML Engineer |
| Version | 3.0 (production-ready) |
| Training Data | 3+ years real-world experience |
| Base Model | Yฤฑldฤฑz Technical University - Physics (GPA: 3.35) |
| Fine-tuning | LENA, AGTEKS, NUMONDIAL |
| Languages | Turkish (native), English (B2), Arabic (A2) |
Training Procedure
Epoch 3 (Current)
Jul 2023 - Present
@ LENA SOFTWARE
- LLM agents for NL-to-SQL translation
- Document & Video QA with RAG pipelines
- Turkish TTS & voice cloning development
- VLM-based industrial fault diagnosis
- Production deployment with Docker + Linux
Epoch 2
Dec 2022 - Jul 2023
@ AGTEKS
- Fabric defect detection with YOLOv8
- Transfer learning for +15% accuracy boost
- Data augmentation strategies
Epoch 1
Sep 2022 - Dec 2022
@ NUMONDIAL DIGITAL
- Object detection & tracking
- Human pose estimation (+20% accuracy)
- Real-time video surveillance
Performance Metrics
+15%
Defect Detection
+20%
Human Detection
99.9%
Uptime
12+
Models Deployed
Usage
Python
from hiring import MLEngineer
# Initialize the model
meryem = MLEngineer.from_pretrained(
"meryemsakin/production-ml-engineer-v3"
)
# Deploy to your team
result = meryem.interview(
company="your_company",
role="ML Engineer",
mode="remote" # or "hybrid", "on-site"
)
print(result)
# โ "Ready to contribute! ๐"Citation
BibTeX
@misc{sakin2024mlengineer,
author = {Meryem Sakin},
title = {Production ML Engineer v3},
year = {2024},
location = {Istanbul, Turkey},
contact = {meryemmsakinn@gmail.com}
}