Principal AI Engineer - Methods at PSTAG | Torre

Principal AI Engineer - Methods

Emma highlights
This highlight was written by Emma’s AI. Ask Emma to edit it.
Full-time

Legal agreement: Employment

Provide your expected compensation while applying (or, if you'd like more context, simply ASK).
location_on
Remote (anywhere)
Posted 25 days ago

Responsibilities


What You Will Do: - Develop AI native applications that extract and process trade compliance data from central EU and member state government sources, including structured data such as XML, JSON, CSV, HTML tables, and APIs. - Develop AI native applications that extract and process trade compliance data from unstructured sources, including PDF documents, legal text, prose regulations, and scanned publications. - Design and build AI native data pipelines that monitor, detect changes, extract, normalize, validate, and release tariff measures data to clients. - Integrate AI/LLM capabilities into extraction workflows using large language models for document understanding, entity extraction, classification, and data structuring. - Design and maintain data models for customs duties, VAT/excise information, and tariff measure metadata. - Ensure data quality through automated testing, benchmarking against official sources, data source and legal source comparison, and data validation pipelines. Required Technical Skills: - 3+ years of professional software development. - Practical experience installing, configuring, and operating Hermes Agent, the self-improving AI agent framework from Nous Research. - Proficiency in any of the following methods: BMAD (Breakthrough Method for Agile AI-Driven Development), GitHub Spec Kit, OpenSec, or Spec-Driven Development (SDD). - Proficiency in at least two programming languages, such as Python, JavaScript/TypeScript, Java, Go, C#, Rust, or Kotlin. - Experience with data extraction and processing, including web scraping, document parsing, and ETL/ELT pipelines. - Experience with structured data, including XML, JSON, CSV, HTML tables, databases, and REST/SOAP APIs. - Experience with unstructured data, including PDFs, legal text, prose regulations, HTML without clear structure, and scanned documents. - Database design and querying, including relational databases like PostgreSQL or document-based databases, schema design, migrations, and indexing. - API development, including building and consuming RESTful APIs. - Version control, including Git workflow, branching strategy, and code review. - Automated testing, including unit, integration, and data validation tests as part of the development workflow. - Self-sufficiency, including the ability to analyze, design, and build complete solutions. - Rapid development, including segmenting development into phases to get results faster. - Influencer, including demonstrating approaches to other team members to lift group maturity. - Communication, including the ability to work with technical, business, and project team members, and participating in and leading discussions. Preferred Technical Skills: - LLM/AI API integration, including OpenAI, Anthropic Claude, or Google Gemini for data processing, document understanding, or content extraction. - AI-assisted development tools, including Claude Code, Cursor, GitHub Copilot, or Windsurf. - NLP and document processing, including OCR, text extraction, entity recognition, and text classification. - Graph databases like Neo4j or vector databases like pgvector. - Observability and monitoring, including SigNoz, Grafana, or Langfuse. - Containerization and deployment, including Docker and CI/CD pipelines.
Closes in:
0
days
0
hours
0
min
0
sec
tune NOT FOR YOU? IMPROVE YOUR RESULTS