AI Systems Engineer

About the role

The AI Systems Engineer will design and build the technical foundation behind Factory Advisors' AI-enabled solutions on customer sites. This role involves working closely with manufacturing leaders, engineers, and operators to turn business requirements into actionable AI solutions.

Responsibilities

• Serve as the technical lead for on-site AI delivery, owning solutions from concept through production deployment, ensuring they are trusted by stakeholders and designed for reuse across future engagements
• Work on-site with manufacturing leaders, engineers, and operators to observe processes and translate ambiguous business requirements into clear technical designs
• Own the design and implementation of AI agents and workflows that solve real business problems and provide measurable impact
• Establish prompt, retrieval, and orchestration components for AI systems
• Integrate AI solutions with customer applications, APIs, and structured/unstructured data sources
• Partner with Network & Security teams to design secure data access, identity, and information retrieval architectures
• Implement monitoring, logging, evaluation, and reliability controls to ensure production readiness
• Support internal teams by mentoring, reviewing designs, and raising the overall technical bar

Requirements

• 2+ Years of software engineering fundamentals with a bias toward clean, maintainable code (Languages such as Python, Java, R, C#, or equivalent)
• Experience with AI agent frameworks, RAG architectures, and orchestration platforms (e.g., LangGraph, Haystack, or equivalent platforms)
• Understanding of data modeling, data access patterns, and system integration, including hands-on experience working with enterprise relational databases and APIs (e.g., Oracle, MySQL, Microsoft SQL Server, or equivalent relational systems)
• Proven ability to design for scalability, reliability, security, and long-term maintainability
• Conceptual understanding of MLOps, monitoring, and operational reliability practices
• Ability to operate without clean APIs or ideal data
• Comfort collaborating with and explaining technical information to non-technical stakeholders
• Strong problem-solving ability, including diagnosing system-level issues, working through incomplete or messy data, and making sound architectural tradeoffs under real-world constraints
• Self-directed, pragmatic, and focused on delivering high-quality working systems—not just ideas

Bonus Points

• Demonstrated ability to design, build, and troubleshoot complex systems including data pipelines, APIs, distributed systems, or platform services in real-world environments
• Experience working in industrial, operational, or highly regulated environments
• Experience integrating solutions into existing ("brownfield") enterprise or operational environments, including legacy systems, data sources, and vendor-managed platforms
• Practical experience with MLOps, system observability, or reliability engineering in production environments
• Experience with Cloud, NoSQL Databases, and Microsoft Dataverse
• Experience with enterprise and cloud native orchestration platforms (e.g., AWS Bedrock AgentCore, Microsoft Power Automate, Google Cloud Vertex, or other equivalent cloud-native platforms)
• Understanding of Model Context Protocol (MCP) and/or Agent-to-Agent (A2A) emerging standards
• Background designing secure enterprise data access patterns
• Experience in consulting, enterprise systems, or production AI environments