Jobs in Japan
Explore hand-picked jobs in Japan for English speakers across tech, education, marketing, and more.
Vetted companies only. Apply from overseas.
Jobs in Japan
Explore hand-picked jobs in Japan for English speakers across tech, education, marketing, and more.
Vetted companies only. Apply from overseas.
MercariThe Customer Support (CS) & Trust and Safety (TnS) Machine Learning (ML) Team keeps Mercari safe for tens of millions of users. We build machine learning models that keep the marketplace safe and reduce manual operations, by detecting prohibited items, harmful behavior, fraud and abuse, and by automating replies to customers. Our models run in real time and decide, within milliseconds, what is safe to show or complete. We own the full life of each model: from the first specification, through training and evaluation, to serving, monitoring and improvement in production. Mercari Engineering Principles are a shared understanding that serves as the foundation of engineering beliefs and behavior at Mercari. These principles ultimately help us achieve Mercari’s mission by defining the ideal state we seek to realize in the long term. Own an ML problem from specification to delivery. Work with product and operation teams to turn a rule or a risk into a measurable target. Then build, ship and maintain the model that meets it. Design, train and evaluate models on image, text and behavioral data, including multimodal deep learning, Japanese NLP, tabular and sequence models. Apply them across item moderation, comment moderation, transaction message moderation, customer auto-reply, and payment fraud prevention. Deploy models as reliable, low-latency real-time services, for example ONNX, TensorRT, and gRPC on Kubernetes. Build CI/CD, rollout and rollback paths, and monitor model health, latency and cost. Build offline evaluation that matches production conditions, verify changes with shadow runs and A/B tests, and detect drift and quality regressions early with dashboards and alerts. Improve model data by working with moderators, customer reports and labeling tools, and find and handle label noise, bias and gaps. Identify where ML can reduce risk or manual work, propose initiatives with a clear business case, and drive them to delivery. Respond quickly to urgent requests such as viral incidents or policy changes, delivering a safe first fix fast and then improving it. Work across boundaries as needed, including data pipelines, backend services and infrastructure. Use AI coding tools to move faster while remaining responsible for the quality of the result. You will build models and evaluations that remain trustworthy despite extreme class imbalance and label noise. You will adapt models and thresholds quickly to changing abuse tactics, viral posts and policy changes without hurting precision for legitimate users. Decisions must meet strict latency and cost limits for tens of millions of users. Items, comments, messages, payments and customer support each have their own data and risks, so you will share methods, tooling and serving across domains and learn new domains with support from senior teammates.
- Shared belief in the mission and values of Mercari Group. - Proficiency in Python. - Daily use of AI coding tools in your development work, with the habit of reviewing and verifying what they produce. - Solid foundation in machine learning and deep learning, with hands-on experience training, evaluating and debugging models (work, research or personal projects). - Eagerness to learn quickly, take end-to-end ownership, and work beyond the boundary of your own area of expertise. - Strong written and verbal communication, with the ability to propose ideas and align stakeholders (product, operations, policy). - English: Proficient (CEFR B2). Required. - Japanese: Basic (CEFR A2). Required.
- 2+ years of professional experience in machine learning or software engineering, with models in production. - Experience in one or more of: computer vision, NLP (Japanese is a plus), fraud or anomaly detection on tabular and sequence data (for example gradient boosting, feature engineering), agentic AI. - Experience serving models in production: Docker, Kubernetes, gRPC or REST, model optimization for latency (for example ONNX, TensorRT, quantization). - Experience with cloud and data tools: GCP, SQL and BigQuery, and ML pipelines (for example Kubeflow, Vertex AI, Apache Beam). - Experience designing offline evaluations and A/B tests, and monitoring models in production. - Knowledge of trust and safety, content moderation or fraud prevention. - Master's or Ph.D. in a related technical field, or the habit of following new research and applying it.
