anjin.techEvery tech job in Japan
12,021 jobs/3,824 companies
HomeJobsCompaniesReports
About anjin.techContactPrivacy PolicyTerms of Service

© 2026 anjin.tech. All rights reserved.

Browse thousands of tech jobs at Japanese startups and companies. Translated for foreign engineers.

Job listings include English summaries for screening. Always verify details on the original job board before applying.

Jobs→株式会社digdig→Machine Learning Engineer - Contract

Machine Learning Engineer - ContractEnglish summary from Japanese

株式会社digdig

✓ Detailed
Salary
スキルに応じてご相談の上決定します。
Job Type
Outsourcing, Side Jobs, Freelance
Apply on HERP

Role summaryEnglish summary from Japanese

English summary for screening — check the original posting before applying.

digdig is a fashion flea market app focused on sustainable fashion. As the first full-time engineer, Mori has led product development. We are seeking a Machine Learning Engineer to design and implement a personalized recommendation system, leveraging existing image embedding mechanisms and user data to improve sales and user experience.

Must-haves

  • Experience designing and developing recommendation systems (collaborative filtering, content-based, etc.)
  • Experience in production operation of machine learning models
  • Experience building ML pipelines with Python
  • Experience designing and conducting online evaluations like A/B testing

Nice-to-haves

  • Experience in recommendation development for fashion services, EC, or marketplaces
  • Experience implementing recommendations using Vision-Language Models (SigLIP, CLIP) and image embeddings
  • Experience utilizing ML platforms (Vertex AI, SageMaker, MLflow)
  • Experience implementing nearest neighbor search using vector databases (FAISS, Qdrant, Weaviate)
  • Experience collaborating with data engineering (BigQuery, dbt)

Tech stack

TypeScriptSigLIP2PythonVertex AISageMakerMLflowFAISSQdrantWeaviateBigQuerydbt

Work style

Contract

About the Company

株式会社digdig

Headquarters
-
Founded
2019-03
Visit Website
Posted4/23/2026
Sourceherp