Senior Data Engineer — Document & AI Pipelines

Tracium GmbH; United States; Hybrid; USD 120,000 - 160,000; Full time

Job summary

Tracium GmbH is building AI-assisted technical documentation software that turns complex manuals into structured, traceable information. You will design data pipelines, data models, and processing workflows to connect source documents, AI processing, and downstream systems.

You will own end-to-end data architecture, ensure reliability, observability, and reproducible reprocessing across multi-tenant environments, collaborating with AI engineers and integrations teams.

Qualifications

• Experience building production data pipelines.
• Strong Python, SQL, and data modelling skills.
• Familiar with workflow orchestration and async processing.
• Emphasis on testing, observability, and data quality.
• Experience with cloud infrastructure and containers.
• Ability to own design from conception to production support.
• Excellent English communication.

Responsibilities

• Design document ingestion and processing pipelines for PDFs, XML, and related data.
• Build workflows for parsing, enrichment, validation, indexing, and export.
• Define data models for document structure, extracted entities, maintenance tasks, and source references.
• Implement document versioning and processing history.
• Ensure pipeline resilience with retries, monitoring, and clear failure handling.
• Collaborate with AI engineers to productionise extraction workflows.
• Support integrations with authoring tools, customer APIs, and ERP systems.

Skills

Data pipelines

Python

SQL

Data modelling

Cloud infrastructure

Containers

Observability

Testing

English communication

Tools

XML

Vector databases

AI data pipelines

Object storage

Job description

About Tracium

Tracium builds AI-assisted technical documentation software that turns complex manuals and engineering documents into structured, traceable information. Starting with maritime, we help technical teams extract maintenance information and create documentation through document intelligence and S1000D authoring.

Your role

You will build the data foundation connecting source documents, AI processing, human review, and downstream systems. Your focus will be reliable processing, clear data models, and traceability throughout the document lifecycle.

What you’ll do

• Design document ingestion and processing pipelines for PDFs, XML, and related technical data.
• Build workflows for parsing, enrichment, validation, indexing, and export.
• Define data models for document structure, extracted entities, maintenance tasks, and source references.
• Implement document versioning, processing history, and reproducible reprocessing.
• Make pipelines resilient through retries, monitoring, automated checks, and clear failure handling.
• Work with AI engineers to productionise extraction and retrieval workflows.
• Support integrations with authoring tools, customer APIs, and ERP systems.

What you bring

• Experience designing and operating production data pipelines.
• Strong Python, SQL, and data modelling skills.
• Experience with workflow orchestration, asynchronous processing, and object storage.
• A practical approach to testing, observability, and data quality.
• Experience with cloud infrastructure, containers, and infrastructure as code.
• The ability to take ownership from initial design through production support.
• Clear communication in English.
• Useful additional experience
  • Document processing, XML.
  • Search indexes, vector databases, or AI data pipelines.
  • Multi-tenant platforms and private deployment environments.

Why join Tracium?

Own the data architecture of a growing product and help make complex technical information dependable, searchable, and usable.

We welcome applicants of all backgrounds. You do not need to meet every listed requirement to apply.