Senior Data AI Engineer

About Sirion

Sirion is the worlds leading AI–native Contract Lifecycle Management (CLM) platform, transforming the end-to-end contracting journey for enterprises. With Agentic AI at the core, the platform’s extraction, conversational search, and AI-enhanced negotiation capabilities have revolutionized contracting across Fortune 500 companies like IBM, Coca-Cola, Citi, and GE. With more than 800 employees across the globe, Sirion comprises a team of AI engineers, legal experts, and researchers who are working relentlessly to build reliable and trustworthy CLM solutions for businesses of tomorrow. Recognized by Gartner, IDC, and Spend Matters as a consistent CLM leader, Sirion continues to set the innovation benchmark for the category.

For more information, visit www.sirion.ai.

ABOUT THE ROLE

We are looking for a hands-on Senior Data & AI Engineer to design, build, and deploy scalable data-driven and AI-powered solutions for procurement transformation. The role combines deep data engineering, unstructured-data processing, LLM application development, and product-oriented delivery. The engineer should be comfortable taking ambiguous business problems and turning them into trusted data models, extraction rules, AI workflows, and production applications.

This is not a prompt-only role. It requires the ability to work through large volumes of unstructured and semi-structured data such as contracts, invoices, POs, RFx documents, supplier files, spreadsheets, emails, PDFs, scanned documents, ERP exports, and procurement-system data, and convert them into reliable structured datasets and intelligent user-facing tools.

KEY RESPONSIBILITIES

• Design, develop, and maintain scalable data pipelines and data products for procurement, sourcing, supplier, contract, spend, invoice, PO, RFx, and ERP data.
• Ingest, parse, normalize, and transform structured, semi-structured, and unstructured data from documents, spreadsheets, databases, APIs, cloud storage, SaaS platforms, and enterprise systems.
• Convert unstructured procurement content into structured tables, entities, relationships, metadata, and business-ready datasets using OCR, document intelligence, NLP, LLMs, parsing frameworks, and rules-based extraction.
• Build extraction workflows for tables, key-value pairs, contract clauses, supplier attributes, spend categories, taxonomies, document classes, duplicate entities, and master-data mappings.
• Define schemas, transformation rules, validation checks, data contracts, confidence scores, exception handling, and human-in-the-loop review workflows for high-quality data capture.
• Design lakehouse, warehouse, data mart, and semantic-layer models using raw, validated, curated, and business-ready data layers.
• Build and deploy AI applications, copilots, chatbots, AI agents, and intelligent automation workflows over procurement data and documents.
• Implement RAG, text-to-SQL, natural-language analytics, function/tool calling, API/database connectivity, agent orchestration, prompt management, and conversation-state handling.
• Apply data quality, lineage, observability, governance, access control, audit logging, LLM evaluation, hallucination checks, guardrails, and production lifecycle management.
• Collaborate with procurement, sourcing, supply chain, finance, analytics, product, and engineering stakeholders to turn use cases into measurable production solutions.

REQUIRED QUALIFICATIONS

• Bachelor’s or Master’s degree in Computer Science, Engineering, Data Science, Information Systems, or a related field; strong hands-on experience is essential.
• 5-8+ years of experience across data engineering, software engineering, AI engineering, ML engineering, analytics engineering, or enterprise application development.
• Proven experience building production-grade data pipelines, data platforms, APIs, and AI/LLM-powered applications.
• Strong hands-on experience converting messy unstructured or semi-structured data into structured, analytics-ready datasets.
• Strong proficiency in Python, SQL, Spark/PySpark, ETL/ELT development, data modeling, API integration, Git, CI/CD, testing, logging, monitoring, and cloud-native deployment.
• Experience with one or more cloud/data platforms such as AWS, Azure, GCP, Databricks, Snowflake, BigQuery, Redshift, Synapse, Delta Lake, Iceberg, or similar.
• Experience with orchestration and transformation tools such as Airflow, Dagster, Prefect, dbt, Azure Data Facto…