AI Data Engineer in New York City, New York at INFO ORIGIN INC

Responsibilities:

• Responsible to support the BDash AI-powered data analytics platform. This individual will contribute to advance data engineering pipelines, AI agent development, and cross-functional quality analytics across different areas of the business such as quality, product engineering, reliability, field service and business strategy.

Agentic AI for Manufacturing Intelligence

• Deep expertise designing and deploying agentic AI systems using agentic frameworks and orchestrators to reason across manufacturing, quality, and post market data, execute multi step analysis, self correct, and drive decisions with limited human intervention.

Production LLM Expertise (Claude Based)

• Production grade experience using Claude LLMs within orchestrated agent workflows, including prompt management, tool calling, structured outputs, guardrails, and audit ready logging.
• Unstructured Structured Manufacturing Data Transformation
• Strong expertise building AI driven data pipelines that transform unstructured medical device data (complaints, CAPAs, investigations, service notes, SOPs, PDFs, emails) into structured, analytics and review ready datasets.

AI Driven Quality & Failure Data Extraction

• Experience developing orchestrated AI pipelines for entity extraction, event classification, failure mode standardization, trend tagging, risk categorization, and summarization aligned to quality and manufacturing taxonomies.

Core ML & Statistical Analysis for Manufacturing

• Solid foundation in predictive modeling, clustering, time series analysis, anomaly detection, and statistical methods applied to manufacturing processes, defects, equipment signals, and failure trends.

Manufacturing Data Platforms & Engineering

• Advanced proficiency with Databricks, Spark, SQL, Delta Lake, and Python to ingest, structure, and analyze large scale manufacturing, quality, and post market data, supporting downstream analytics and AI systems.

Quality, CAPA & Root Cause Analytics

• Demonstrated ability to correlate complaints, NCRs, CAPAs, and service data with upstream manufacturing signals using data driven root cause and investigation approaches.

Enterprise & Regulated Systems (SAP Centric)

• Hands on experience integrating and analyzing data from SAP Tahiti, Salesforce, TrackWise, and QMS platforms while maintaining traceability, data integrity, and compliance in regulated environments.

Must Have

• AI Engineering
• Anthropic Claude AI
• MCP Server Customization
• Microsoft Azure Databricks
• SalesForce
• SAP Tahiti
• Trackwise

Nice To Have

• Microsoft Power Business Intelligence (BI)
• Speech to Text tools
• Text to Speech Tools