5 дней назад
Machine Learning Engineer (Search ML)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Machine Learning Engineer (Search ML): Designing and optimizing item search and discovery capabilities for a high-velocity C2C marketplace with an accent on hybrid search, learning-to-rank, and agentic shopping. Focus on bridging the semantic gap between user queries and fragmented UGC while operationalizing advanced LLM architectures.
Location: Hybrid in Tokyo, Japan
Company
is a leading C2C marketplace app focused on circulating all forms of value to unleash human potential.
What you will do
- Drive the optimization of item search and discovery capabilities and take end-to-end ownership of core search business logic.
- Design and deploy state-of-the-art ML models and training pipelines, incorporating Hybrid Search, Learning-to-Rank, and Agentic Shopping.
- Develop standardized evaluation and experimentation infrastructure, including offline evaluation frameworks and online A/B testing guardrails.
- Collaborate with infrastructure and product teams to align on scalability, latency, reliability, and cost efficiency.
Requirements
- 3+ years of professional experience in Machine Learning or Search Engineering.
- Proven track record of optimizing search experiences using hybrid retrieval, learning-to-rank, and embedding-based search.
- Hands-on experience with production-grade ML serving infrastructure such as online inference services or feature stores.
- English: Business level or above.
- Strong collaborative and communication skills to align diverse technical teams.
Nice to have
- 5+ years of software engineering experience focusing on large-scale backend architectures.
- Deep technical expertise in distributed systems and high-concurrency/low-latency tuning.
- Japanese language proficiency.
Culture & Benefits
- Full Flextime with no core time.
- Work environment based on principles of Passion For The Product, Growing Together, and Open Collaboration.
- Strong commitment to Inclusion & Diversity.
- Opportunity to solve complex challenges related to high-velocity inventory turnover and UGC semantic bridging.
Hiring process
- Application screening followed by a skill assessment on HackerRank or GitHub.
- Multiple rounds of interviews depending on the position.
- Online reference checks prior to the final offer.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →