About the role
TL;DR
Data Engineer to build an unstructured data context layer for an investment group.
- •Neurons Lab is seeking a part-time Data Engineer to build a context layer for a European private investment group.
- •This role focuses on unstructured data, handling ingestion, entity resolution, and PII management.
- •Key Responsibilities Ingest data from calls, email, Slack, and other sources, including historical data.
- •Implement identity and entity resolution across various data types.
- •Build document parsing and chunking pipelines for unstructured data.
- •Manage PII detection, redaction, and retention logic.
- •Orchestrate data pipelines using tools like Airflow.
- •Requirements 4+ years of data engineering experience, with a focus on unstructured/semi-structured data.
- •Strong Python and solid SQL skills.
- •Experience with unstructured data pipelines, embedding/retrieval infrastructure, and API integration.
- •Familiarity with AWS and/or GCP data stacks.
- •Knowledge of GDPR and data lineage/provenance patterns.
Required skills
PythonSQLAirflowAWSGoogle CloudPostgreSQLNeo4jDockerKubernetesSlackGDPR
Nice-to-have skills
LangChainLLMs
Domain expertise
fintech
Tech stack
PythonSQLAirflowAWSGoogle CloudPostgreSQLNeo4jGitLinuxDockerKubernetesSlack