Назад
Company hidden
9 часов назад

Tech Lead Manager (AI)

Формат работы
hybrid
Тип работы
fulltime
Грейд
lead
Английский
b2
Страна
UK/US/SK
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Tech Lead Manager (AI): Building and leading the founding team for Jockey Core, a reasoning LLM that decomposes video queries, controls retrieval and segmentation, and produces actionable answers with an accent on production-scale inference, model efficiency, and end-to-end serving. Focus on designing serving architecture, optimizing latency, throughput, and cost, and scaling a hands-on ML infrastructure team.

Location: Seoul, South Korea; hybrid work

Company

hirify.global builds multimodal AI models and production-scale video intelligence infrastructure for media, entertainment, sports, security, and government.

What you will do

  • Build and lead the founding team for Jockey Core, including hiring, team growth, delivery, and technical direction.
  • Own the end-to-end roadmap for Jockey Core, from model and engine selection through efficiency optimization, production serving, and scale-out.
  • Lead critical model-serving and inference architecture decisions and set the technical bar through design reviews.
  • Evaluate latency, throughput, and cost tradeoffs using measured data.
  • Partner with the Pegasus, agent, and infrastructure teams on capacity planning and service-level objectives.
  • Adopt AI-assisted development tools such as Claude, Gemini, and GPT to improve team productivity.

Requirements

  • Track record leading ML or infrastructure teams as a hands-on technical lead or manager, ideally while founding or scaling a small team.
  • Deep production experience serving and optimizing large-scale LLM inference using vLLM, TensorRT-LLM, SGLang, or similar systems.
  • Experience with batching and scheduling, quantization, disaggregated prefill/decode, and speculative decoding.
  • Ability to drive ambiguous technical decisions using latency, throughput, and cost data.
  • Excellent communication and people leadership skills.
  • Professional work is based in Seoul, South Korea under a hybrid arrangement.

Nice to have

  • Experience with model compression, including pruning, quantization-aware training, or distillation.
  • Experience productionizing reasoning or agentic LLMs.
  • Experience with multi-region or multi-cluster serving and large-scale GPU capacity planning.
  • Contributions to or customization of an LLM inference server's internals.
  • Master's or PhD in Machine Learning, Computer Science, or a related field.

Culture & Benefits

  • Global team working with global B2B customers, with autonomy and collaboration.
  • Latest MacBook, home-office equipment support worth approximately KRW 700,000, and equipment replacement every three years.
  • Unlimited LLM tokens for technical roles.
  • Annual professional development budget of approximately KRW 1.4 million for courses, conferences, and memberships.
  • English education, global buddy program, commuting taxi support at night and on weekends, and office meals and snacks.
  • Annual health checkups for the employee and one family member, group insurance, flu vaccination support, and a two-week paid holiday break at year end.

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 →