Senior Machine Learning Engineer, Agentic Context Retrieval and Search (Nova)
Контакты
150 000 - 250 000$
Формат работы
remote (только USA)
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
US
aillmragelasticsearchmachine learninginformation retrievalsearchembeddingslearning to rank
Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
развернуть
$150к-250к/год
$200к$220кмедиана$240к
По похожим ролям (49) ~ $220к/год
На СНГ рынке: $4.6к/мес ($3.7к - $6к)
91
Крутая вакансия
развернуть
Чётко очерченная senior-роль с ответственностью за production-системы поиска для ИИ в зрелой продуктовой компании; требование учёной степени сужает круг подходящих специалистов.
Нужна учёная степень
Современный стек ИИ
Много самостоятельности
Зрелый продукт
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior Machine Learning Engineer, Agentic Context Retrieval and Search (Nova) (Machine Learning/Information Retrieval): Building retrieval infrastructure and search subagents for AI agents across structured and unstructured customer data with an accent on semantic query understanding, hybrid retrieval, and evidence-grounded responses. Focus on designing multi-hop search, evaluating ranking quality, reducing hallucinations, and operating reliable production systems at scale.
Location: Remote - US; additional locations include Chicago, San Francisco, Atlanta, Austin, Boston, Denver, and New York.
Salary: $150K–$250K US base salary annually, determined by work location, skills, experience, education or training, and internal equity.
Company
hirify.global is an AI customer engagement platform for enterprise brands, enabling customer-data activation, cross-channel experiences, and AI-powered engagement through Nova Intelligence.
What you will do
Build retrieval across structured sources such as tables, SQL, dashboards, and code, as well as unstructured documents, tickets, chats, and media.
Develop semantic query understanding for agents, including query rewriting, decomposition, intent classification, and entity resolution for multi-turn workflows.
Build pipelines for entities, embeddings, summaries, and metadata, keeping customer-data representations fresh.
Develop search subagents that select retrieval strategies, perform multi-hop searches, assess result sufficiency, and detect retrieval failures.
Measure retrieval and response quality using ranking metrics, LLM judges, human labels, offline benchmarks, regression detection, and online tests.
Mentor engineers and help define Nova’s technical direction.
Requirements
5+ years of hands-on machine learning engineering experience putting complex models into production at scale, including search, information retrieval, or recommendation systems.
Master’s or PhD in Computer Science, Machine Learning, AI, or a related field.
Deep information retrieval expertise covering lexical retrieval such as BM25, dense retrieval with embeddings and ANN indexes, hybrid retrieval, and learning-to-rank.
Production experience with Elasticsearch, OpenSearch, or Vespa, including relevance tuning and reranking.
Hands-on experience with RAG, query rewriting, reranking, and grounding techniques that reduce hallucinations.
Experience building retrieval-based agents, including multi-hop search or sufficiency checks.
Strong evaluation practice with offline benchmarks, regression detection, A/B testing, and labeling pipelines.
Ability to follow current research and apply it by shipping reliable changes that measurably improve customer experience.
Nice to have
Experience with LLM APIs from multiple providers, including Anthropic, OpenAI, and Google, with tool calling and prompt caching.
Experience indexing and ranking structured and unstructured data in the same system.
Culture & Benefits
Full-time employment with remote work limited to the US.
Autonomy across research, experimentation, production delivery, and technical direction.
Values include ownership, growth mindset, collaboration, and transparency.
hirify.global supports a diverse and inclusive workplace and considers qualified applicants without regard to protected characteristics.
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 →