Part-Time Data Engineer — Unstructured Data & AI Pipelines

Neurons Lab LTD.; Warszawa; On-site; PLN 83,000 - 152,000; Part time

Job summary

Neurons Lab LTD. seeks a part-time Data Engineer to build and operate unstructured data pipelines, including transcripts, emails, Slack chats, and documents.

You will implement entity resolution, embedding and retrieval systems, and scalable orchestrations to support a privacy-conscious data layer for a European investment context. The role emphasizes hands-on data engineering with emphasis on ingestion, backfill, and incremental syncing, while keeping costs and latency in check within a small,

Qualifications

• 4+ years in data engineering with unstructured/semi-structured work
• Experience integrating many third-party APIs into one coherent store
• Experience building pipelines feeding an LLM / retrieval system
• Experience handling sensitive personal data in a regulated environment
• Comfortable being the only data engineer on a small (2.5-FTE) pod, part-time
• Clear written English for handover documentation

Responsibilities

• Stand up capture and ingestion from calls, email, Slack, and messengers with speaker attribution
• Backfill archive data: emails, chats, decks, and portfolio updates
• Build document parsing for PDFs, spreadsheets, and slide decks
• Implement identity/entity resolution across sources
• Build chunking and embedding pipelines and load vector/graph stores
• Implement incremental sync with a connector layer and handle edits/deletions
• Attach access scope and provenance to records at ingestion
• Run PII detection, redaction, and retention logic
• Orchestrate pipelines with Airflow/Step Functions with monitoring
• Control cost and latency with batching and storage tiering
• Write runbooks for client handover

Skills

Python

SQL

Unstructured data pipelines

Embedding systems

Vector stores

API integration

Airflow

Cloud stack

PII handling

Data governance

English writing

Tools

pgvector

OpenSearch

Pinecone

Airflow

Step Functions

Job description

Neurons Lab LTD. seeks a part-time Data Engineer to build and operate unstructured data pipelines, including transcripts, emails, Slack chats, and documents.

You will implement entity resolution, embedding and retrieval systems, and scalable orchestrations to support a privacy-conscious data layer for a European investment context. The role emphasizes hands-on data engineering with emphasis on ingestion, backfill, and incremental syncing, while keeping costs and latency in check within a small,