13 часов назад
Senior Engineering Manager, Search for our Cognition System (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Senior Engineering Manager, Search for our Cognition System (AI): Leading the development of production-grade search and retrieval infrastructure for millions of hours of video, with an accent on vector, lexical, hybrid, multimodal, and agentic search. Focus on scaling ingestion and indexing, orchestrating multi-turn and parallel search sessions, maintaining search quality and reliability, and building a team of engineers and scientists.
Location: Hybrid in Seoul, South Korea
Company
builds multimodal AI models that understand video across sight, sound, and motion, powering production-scale workloads for media, entertainment, sports, security, and government.
What you will do
- Own the end-to-end search system, including vector and ANN indexing, lexical retrieval, hybrid fusion, reranking, and temporal segment-level search.
- Build an agentic search harness that infers human and agent intent and orchestrates multi-turn, session-based, parallel, and subagent-driven searches.
- Scale ingestion and index creation across millions of hours of video using Marengo embeddings and Pegasus.
- Set the search-quality bar and improve reliability, system performance, and high-RPS production behavior.
- Align retrieval strategy, API contracts, and system boundaries with Research, Training, Platform, Infrastructure, and Product.
- Recruit and lead engineers and scientists while setting technical standards through architecture reviews, code reviews, and mentorship.
Requirements
- 7+ years of experience building production ML or search systems, with deep expertise in search, retrieval, or recommendation at scale.
- Experience building and leading engineering teams, hiring senior individual contributors, and developing engineers and scientists.
- Deep knowledge of information retrieval, including embedding-based search, lexical search with BM25, OpenSearch or Elasticsearch, hybrid retrieval, reranking, and score normalization.
- Strong system-design skills across ML infrastructure, distributed systems, and developer-facing platforms.
- Experience with agentic search systems and multimodal or video search and retrieval.
- Good English communication skills, both verbal and written.
Nice to have
- Familiarity with knowledge graph construction, entity resolution, or graph-backed retrieval.
Culture & Benefits
- Hybrid work combining autonomy and collaboration.
- Global team serving B2B customers worldwide.
- MacBook and home-office equipment support worth up to KRW 700,000, with equipment renewal every three years.
- Monthly corporate card allowance of up to KRW 600,000 for meals, transportation, and other expenses.
- Office snack bar, annual health checkup, two-week winter break, and English education support.
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 →