Personalized Recommendation Systems Engineer
We are seeking a skilled engineer with strong experience in building recommendation systems to join our growing team. You will play a critical role in designing and optimizing personalized experiences for millions of users by transforming raw data into insights and automated systems.
About the Role:
The ideal candidate will have hands-on experience building and deploying recommendation systems, including matrix factorization, deep learning-based recommenders, and implicit/explicit feedback models. They will also have proficiency in Python and machine learning libraries such as Scikit-learn, TensorFlow, PyTorch, and LightFM.
Key Responsibilities:
1. Design, build, and deploy scalable recommendation engines using collaborative filtering, content-based methods, or hybrid approaches.
2. Develop user profiling models using clickstream and behavioral data.
3. Leverage AI-driven product tagging to enhance metadata quality and retrieval.
4. Analyze macro and micro fashion trends to influence product rankings.
5. Extract insights from large-scale user data and convert them into actionable models.
6. Work closely with engineers and product managers to integrate models into production.
7. Develop and monitor metrics for model performance and user engagement impact.
Requirements:
8. 2+ years of experience in data science, ideally in e-commerce or consumer-tech.
9. Hands-on experience building and deploying recommendation systems (e.g., matrix factorization, deep learning-based recommenders, implicit/explicit feedback models).
10. Proficiency in Python and machine learning libraries (e.g., Scikit-learn, TensorFlow, PyTorch, LightFM).
11. Experience with data analysis tools such as SQL, Pandas, and Jupyter.
12. Strong grasp of personalization techniques and user segmentation strategies.
13. Solid understanding of product ranking using behavioral data and trend signals.
14. Experience working with large-scale data pipelines and A/B testing frameworks.
15. Strong communication and problem-solving skills.
Preferred Qualifications:
16. Experience in the fashion or lifestyle e-commerce domain.
17. Knowledge of modern MLops workflows and model monitoring tools.
18. Familiarity with cloud platforms (AWS, GCP) and tools like Airflow or DBT.
19. Background in NLP or computer vision for fashion tagging is a plus.