AI Data Engineer YozmaTech $

Our client is looking for an AI Data Engineer to help build, maintain, and improve internal and client-facing LLM-powered systems. This role sits at the intersection of data engineering, retrieval infrastructure, and production AI operations, focusing on reliability, retrieval quality, scalability, and operational excellence.

Key Requirements

• Strong programming skills, especially in Python.
• Experience building ETL and data pipelines in production environments.
• Strong SQL skills and experience with relational databases, preferably PostgreSQL.
• Experience with search and retrieval systems, including OpenSearch, Elasticsearch, or similar platforms.
• Familiarity with vector databases, embeddings workflows, and large-scale document indexing.
• Experience with cloud platforms such as AWS and related infrastructure services.
• Familiarity with Git, CI/CD pipelines, and modern engineering workflows.
• Strong problem-solving skills and comfort working across data, infrastructure, and AI application layers.
• English – Upper-Intermediate or higher.

Will be plus

• Experience working on RAG systems, internal knowledge assistants, or search-heavy AI applications.
• Familiarity with observability stacks, distributed systems, and workflow orchestration tools.
• Experience with access control, permission-aware systems, and auditability in enterprise environments.
• Exposure to evaluation frameworks for LLM systems and model benchmarking.

What you will do

• Maintain and improve ingestion and enrichment pipelines for internal and client content, including parsing, extraction, normalization, metadata enrichment, deduplication, and quality monitoring.
• Improve indexing and retrieval quality through chunking and segmentation refinements, embedding and index update workflows, metadata filtering, and caching.
• Support hybrid retrieval architectures combining vector search, keyword or BM25 search, and metadata-aware filtering.
• Implement and maintain access-aware retrieval by propagating and enforcing document permissions at indexing and query time, including audit logs and validation tests.
• Improve source attribution so responses consistently point to the correct documents, sections, and references in a reliable format.
• Extend and harden tool execution, workflow orchestration, and automations, including retries, timeouts, idempotency, concurrency controls, and run history.
• Develop and maintain evaluation and regression testing frameworks, including golden datasets, automated scoring, and structured comparisons across LLM providers and models.
• Operate AI systems in production, including logs, metrics, tracing, alerting, incident response, performance tuning, cost monitoring, and runbook documentation.
• Build scalable infrastructure to process, embed, index, and search very large document collections efficiently.

Benefits

• Direct access to clients and meaningful products.
• Flexibility to work remotely or from our offices.
• A-team colleagues and a zero-bureaucracy culture.
• Opportunities to grow, lead, and make your mark.

Everyone’s welcome – diversity makes us better. We create a space where you can thrive as you are.