Principal Orchestration Engineer

SUMMARY:

Motion Industries is seeking a Principal Orchestration Engineer to architect and build the next generation of intelligent applications. Reporting to the Director of Enterprise Intelligence, you are the technical leader responsible for designing the "Data-to-Intelligence" pipeline—the systems, frameworks, and orchestration layers that transform our data into AI-powered agents and applications. This is NOT a machine learning research role. You won't be training models or fine-tuning LLMs. Instead, you'll be the expert at using AI as a building block—integrating LLM APIs (OpenAI, Anthropic, etc.) with our data infrastructure to build production-grade intelligent systems. This is a hands-on technical leadership role. You will personally build production AI applications while establishing the architectural patterns, frameworks, and best practices that enable the broader team to scale our AI capabilities.

What You'll Actually Do

Building AI Applications (60-70% of your time):

• Build AI Agents: Design and implement multi-agent systems using a combination of frameworks like LangGraph and embedded 3rd party agents, like Genie and CoPilot that orchestrate LLM API calls to solve business problems
• RAG Architecture: Build retrieval-augmented generation systems that ground LLM responses in Motion's data (vector databases, semantic search, chunking strategies)
• Data Integration: Connect AI agents to our data lakes, operational systems, and external APIs— ensuring agents have access to the right context
• Orchestration & Workflows: Design complex agent workflows (sequential, parallel, hierarchical) that coordinate multiple LLM calls and data operations
• Evaluation & Monitoring: Build automated testing and evaluation frameworks to measure agent accuracy, latency, cost, and business impact
• Production Engineering: Debug and optimize production AI applications for performance, cost, and reliability

  Technical Leadership (30-40% of your time):

• Establish Standards: Define best practices for RAG architectures, prompt engineering, agent design patterns, and LLMOps
• Framework Development: Build internal frameworks and libraries that make it easy for other engineers to build AI applications
• Mentorship: Code review, pair programming, and upskilling data engineers and software engineers on AI application development
• Architecture: Design reference architectures for common AI use cases (conversational agents, analytical assistants, automation agents)
• Collaboration: Partner with the Director of Enterprise Intelligence, product teams, business intelligence, and business units to identify and prioritize high-value AI use cases
• Thought Leadership: Document and share learnings internally; represent Motion's AI capabilities Key Responsibilities AI Application Architecture &

  Development (50%)

• Design and build production AI agents and intelligent applications using LLM APIs (OpenAI, Anthropic, Azure OpenAI, etc.)
• Implement RAG (Retrieval-Augmented Generation) systems including vector database selection, embedding strategies, chunking logic, and metadata tagging
• Build multi-agent orchestration systems that coordinate LLM calls, data retrieval, and business logic
• Create reusable frameworks and patterns for common AI application needs
• Optimize for cost (token usage), latency, and quality across all AI applications

  Data-to-AI Pipeline Engineering (30%)

• Design the "semantic layer" that helps AI agents understand Motion's business logic, data relationships, and domain context
• Build robust data pipelines that prepare, chunk, and embed data for AI consumption
• Implement vector databases and semantic search systems
• Ensure AI agents can reliably access and query our data warehouse and operational systems
• Partner with data engineering team to optimize data flows for AI use cases

  LLMOps & Production Excellence (15%)

• Implement CI/CD pipelines for AI applications (versioning, testing, deployment)
• Build comprehensive monitoring and observability for agent performance, cost, and quality
• Establish "Guardrails-as-Code" to prevent data leakage, prompt injection, and ensure compliance
• Create automated evaluation frameworks (evals) to measure agent accuracy and business outcomes
• Partner with DevOps on infrastructure, security, and cost optimization Enablement & Leadership (5%)
• Lead training workshops on AI application development for data and software engineers
• Create documentation, reference implementations, and best practice guides
• Mentor team members on prompt engineering, agent design, and RAG architectures
• Collaborate with the Director of Enterprise Intelligence on team roadmap, hiring strategy, and capability development

  Required Qualifications

  Technical Expertise Software Engineering Foundation:

• Expert-level Python (this is a Python-heavy role)
• Strong SQL and data querying skills
• API design and integration experience (RESTful APIs, webhooks, event-driven systems)
• Software engineering best practices (version control, testing, CI/CD, code review)
• Experience with modern application frameworks

  Data Engineering Experience:

• 3+ years working with modern data stacks (Databricks, Azure)
• Understanding of data modeling, ETL/ELT patterns, and data warehouse architecture
• Experience with data orchestration tools
• Knowledge of data quality, governance, and security practices

  AI Application Development:

• 2+ years building production applications using LLM APIs (OpenAI, Anthropic, Azure OpenAI, etc.)
• Hands-on experience with LLM frameworks (LangChain, LlamaIndex, LangGraph, Haystack, or similar)
• Deep expertise building RAG (Retrieval-Augmented Generation) systems at scale
• Production experience with vector databases (Pinecone, Weaviate, Milvus, Chroma, pgvector, etc.)
• Proven track record designing and implementing multi-agent systems or complex LLM workflows
• Strong prompt engineering skills and understanding of LLM capabilities/limitations Infrastructure & DevOps:
• Experience with containerization (Docker) and cloud platforms (AWS, Azure, GCP)
• Understanding of API rate limiting, caching, and optimization strategies
• Knowledge of security best practices for AI applications (data privacy, prompt injection prevention)
• Familiarity with monitoring and observability tools

  Experience & Background

• 8+ years in software engineering, data engineering, or related technical roles
• 2+ years specifically building AI-powered applications (using LLMs via APIs)
• 3+ years in a senior or lead capacity, with demonstrated technical leadership
• Proven ability to design and implement systems that scale to enterprise requirements
• Track record of successfully leading technical initiatives from concept to production
• Experience working in cross-functional teams and translating business needs into technical solutions

  LICENSES & CERTIFICATIONS: None required.

  SUPERVISORY RESPONSIBILITY: No Supervisory Responsibility

  BUDGET RESPONSIBILITY: No

  COMPANY INFORMATION:

  Motion offers an excellent benefits package which includes options for healthcare coverage, 401(k), tuition reimbursement, vacation, sick, and holiday pay.

  Not the right fit?  

• Let us know you're interested in a future opportunity by joining our Talent Community onjobs.genpt.comor create an account to set up email alerts as new job postings become available that meet your interest!

  GPC conducts its business without regard to sex, race, creed, color, religion, marital status, national origin, citizenship status, age, pregnancy, sexual orientation, gender identity or expression, genetic information, disability, military status, status as a veteran, or any other protected characteristic. GPC's policy is to recruit, hire, train, promote, assign, transfer and terminate employees based on their own ability, achievement, experience and conduct and other legitimate business reasons.