У роли понятная специализация в быстроразвивающейся области ИИ, но из-за аутсорсингового формата меньше ясности о проекте и долгосрочной работе команды.
Аутсорсинговый формат
Современный стек ИИ
Понятные задачи
Гибкий формат
Мэтч & Сопровод
Покажет вашу совместимость и напишет письмо
Создать профиль и узнать мэтч
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Agentic AI Engineer (Cheminformatics) (LLM/RAG): Building knowledge infrastructure for AI agents in complex scientific and technical workflows with an accent on document processing, retrieval architectures, vector databases, and structured knowledge repositories. Focus on designing scalable RAG pipelines, optimizing context and retrieval quality, and implementing source attribution and evaluation mechanisms.
Location: Remote from Serbia
Company
Software Country provides custom software development services focused on complex high-load applications, AI and BI solutions, and mobile applications, with 30 years of experience.
What you will do
Design and build knowledge bases for AI agents, including RAG systems, internal wikis, and structured knowledge repositories.
Develop document ingestion and processing pipelines for collecting, parsing, cleaning, chunking, enriching, and indexing information from multiple sources.
Design retrieval architectures using semantic, keyword, and hybrid search with metadata filtering; build embedding pipelines and vector database infrastructure.
Integrate documents, APIs, databases, internal tools, and external repositories into agent knowledge workflows.
Optimize retrieval quality and context construction, implement source attribution and traceability, and collaborate on integration with AI agents and conversational interfaces.
Requirements
More than 6 years of professional experience.
Strong understanding of LLMs, RAG architectures, and how AI agents consume external knowledge.
Hands-on experience building production-grade RAG pipelines and knowledge bases.
Experience with vector databases, embedding models, semantic search, information retrieval, and document ingestion, parsing, chunking, indexing, and retrieval pipelines.
Strong understanding of structured and unstructured data management.
Experience integrating APIs, databases, and different knowledge sources.
Strong Python development skills.
Ability to design scalable and maintainable knowledge infrastructure for production AI applications.
Nice to have
Experience building knowledge bases for multi-agent systems.
Knowledge graphs, ontologies, graph-based retrieval, hybrid search, reranking, query expansion, or other advanced retrieval techniques.
Experience with LangChain, LlamaIndex, Haystack, OpenSearch, Pinecone, Weaviate, or Qdrant.
Experience with Amazon Bedrock and AWS infrastructure.
Experience with scientific literature, technical documentation, or research datasets.
Background in chemistry, cheminformatics, or drug discovery.
Culture & Benefits
Remote work from Serbia with a flexible work schedule.
Collaboration through a B2B contract with payment in USD or EUR according to preference, or through a labor contract.
Opportunities for professional growth.
Company laptop provided.
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 →