Key skills
AWSAzureCloudDistributed SystemsElasticSearchETLGoogle Cloud PlatformJavaPythonAILLMRAGLangChainLlamaIndexAgenticData EngineeringGCPGoogle CloudElasticsearch
About this role
Role Overview
- Design and implement GraphRAG pipelines that combine knowledge graphs with LLM-based retrieval systems
- Build scalable data ingestion, transformation, and enrichment pipelines for structured and unstructured data
- Integrate LLMs and embedding models into production systems (RAG, semantic search, agent workflows)
- Work with workflow automation tools (e.g., n8n) to orchestrate complex data and AI pipelines
- Build clean, production-grade APIs for AI and data services
- Optimize performance of retrieval, indexing, and transformation pipelines
- Ensure reliability, observability, and scalability of AI-driven backend systems
- Collaborate with product, data, and backend teams to design end-to-end AI features
- Collaborate with customer-facing teams and with Research on the research agenda
- Debug complex issues across distributed data and AI pipelines
Requirements
- 4+ years of experience in backend or data engineering (Java, Python, or similar strongly typed language)
- Experience designing and building LLM pipelines, ETL workflows, backend data processing systems, and prompt engineering, including evaluation
- Strong understanding of APIs and backend system design
- A deep understanding of the LLM ecosystem, including model architectures and fine-tuning approaches
- Hands-on experience with structured and/or unstructured data processing
- Experience integrating external services or APIs in production systems
- Strong problem-solving skills and ability to work with complex data flows
- Degree in Computer Science, Engineering, or equivalent practical experience
- Proficiency in English, both written and verbal
- Nice to have: Experience with RAG systems, LLM orchestration, or AI retrieval pipelines
- Familiarity with vector databases, embeddings, or semantic search systems
- Experience with n8n or similar workflow automation tools
- Knowledge of knowledge graphs, RDF, SPARQL, or GraphDB-like systems
- Experience with Elasticsearch / OpenSearch or other search indexing systems
- Exposure to LLM frameworks (LangChain, LlamaIndex, etc.)
- Experience with multi-agent systems or complex agentic workflows
- Experience with distributed systems and scalable data infrastructure
- Familiarity with cloud platforms (AWS/GCP/Azure) and containerized deployments
- Experience in early-stage development – you enjoy the zero-to-one phase
- Actively contributed to relevant open-source projects or publications
Tech Stack
- AWS
- Azure
- Cloud
- Distributed Systems
- ElasticSearch
- ETL
- Google Cloud Platform
- Java
- Python