Agentic AI engineer in cheminformatics

We have 30 years of expertise in designing and building custom software systems. We provide software development services focusing on complex high-load applications, AI and BI solutions, and mobile apps. We are looking for an AI Engineer to design and build the knowledge infrastructure that powers AI agents in complex scientific and technical workflows. The focus is on building the underlying knowledge layer that agents rely on transforming unstructured and structured information into accessible, searchable, and contextualized knowledge.

• Design and build knowledge bases for AI agents, including RAG systems, internal wikis, and structured knowledge repositories.
• Develop document ingestion and processing pipelines to collect, parse, clean, chunk, enrich, and index information from different sources.
• Design retrieval architectures that enable agents to access relevant information using semantic search, keyword search, hybrid search, and metadata filtering.
• Build and maintain embedding pipelines, vector databases, and other retrieval infrastructure.
• Integrate knowledge sources such as documents, APIs, databases, internal tools, and external information repositories.
• Design knowledge structures, metadata schemas, taxonomies, and relationships between information to improve discoverability and retrieval quality.
• Implement mechanisms for knowledge updates, versioning, deduplication, and synchronization to keep information accurate and current.
• Optimize retrieval quality, context construction, and information delivery for LLM-powered agents.
• Implement source attribution, traceability, and mechanisms to evaluate the accuracy and relevance of retrieved information.
• Collaborate with AI and software engineers to integrate knowledge infrastructure into agent workflows and conversational interfaces.

• Strong understanding of LLMs, RAG architectures, and how AI agents consume and use external knowledge.
• Hands-on experience building production-grade RAG pipelines and knowledge bases.
• Experience with vector databases, embedding models, semantic search, and information retrieval.
• Experience designing 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, maintainable knowledge infrastructure for production AI applications.
• Будет плюсом: Experience building knowledge bases for multi-agent systems; Familiarity with knowledge graphs, ontologies, and graph-based retrieval; Experience with hybrid search, reranking, query expansion, and advanced retrieval techniques; Familiarity with frameworks such as LangChain, LlamaIndex, or Haystack; Experience with vector databases such as OpenSearch, Pinecone, Weaviate, or Qdrant; Experience with Amazon Bedrock and AWS infrastructure; Familiarity with knowledge management systems, internal wikis, and enterprise search; Experience with RAG evaluation, retrieval observability, and quality monitoring; Experience working with scientific literature, technical documentation, or research datasets; Background in chemistry, cheminformatics, or drug discovery

• Collaboration via a B2B contract with payments in USD or EUR, depending on your preference, or through a labor contract
• Flexible work schedule.
• Possibility to work remotely
• Opportunities for professional growth.
• A company laptop to ensure a comfortable and efficient work setup.