
Lead AI Architect | Engineering AI & Agentic Systems
Apolis · Harrisburg, PA
Strong hiring record · median 15 days open
- First seen
- 19 November 2026
- Reposted
- Not since September 2026
All reasons
In its favour
- Posted today
- Still listed on the employer's own board
ROLE NAME
Lead AI Architect | Engineering AI & Agentic Systems
LOCATION Harrisburg, PA (REMOTE)
JOB DESCRIPTION
Seeking a hands-on Lead AI Architect to establish and lead the engineering-specific AI architecture. This role will design and scale secure, production-ready AI agents and engineering workflow automation across CAD, PLM, CAE/simulation, requirements, and product development processes.
The architect will be the technical authority for engineering AI architecture, solution approaches and vendor integration, working with TE’s central IT AI platform team while owning the engineering domain context, tools, solution patterns, technical quality, and long-term management of AI solutions deployed. The role will initially combine architecture and hands-on technical delivery, then hire and lead an engineering AI development team as demand grows.
# Key Responsibilities
## Engineering AI architecture and strategy
Own and evolve the engineering AI reference architecture, integrated with central IT AI services (e.g., enterprise AI gateway, model access, identity, agent registry, orchestration and shared observability) without duplicating them.
- Design domain-specific capabilities, including engineering ontology, knowledge graphs where justified, semantic/context services, retrieval, reusable agent tools and engineering workflow patterns.
- Make informed build-versus-buy and technical-pattern decisions, choosing among LLM agents, deterministic rules, geometric computation, simulation, surrogate models and hybrid approaches.
## Engineering context and knowledge architecture
- Define relationships and traceability among requirements, CAD models, parts, assemblies, BOMs, materials, revisions, simulations, test results and engineering documentation.
- Architect grounded retrieval, engineering RAG/graph retrieval, metadata and provenance, revision-aware context, and fine-grained access controls.
- Partner with OneData/Databricks and application owners on trusted engineering data pipelines and context services.
## Agents, integrations and MCP engineering
- Lead architecture and hands-on development of AI agents and multi-step engineering workflows, including tool calling, state, approvals, exception handling and auditable actions.
- Design, build and sustain engineering MCP servers, API adapters and integration services for CAD, PLM, CAE and adjacent applications; assess vendor-managed versus custom capabilities.
- Establish secure authentication/authorization, identity propagation, interface contracts, versioning, CI/CD, evaluation, monitoring and production support for agents and MCP services.
## Vendor AI solution assessment and technical authority
- Lead technical due diligence and architecture reviews for CoLab automated design review, Synera simulation workflows, PTC Creo/Windchill AI, Ansys AI, AWS consulting and future engineering AI partners.
- Challenge vendors on underlying mechanisms (LLMs versus rules/algorithms), CAD geometry interpretation, simulation validity, system interfaces, data handling, security, accuracy, extensibility and operational support.
- Define technical acceptance criteria, reference architectures, documentation, reusable assets, handover requirements and ownership boundaries to minimize avoidable vendor lock-in.
## AI security and governance
- Work with cybersecurity, AI governance and application teams on onboarding new vendor solutions or existing vendor AI solutions and secure integrations needed.
## Delivery leadership and team development
- Own solution architecture for engineering AI use cases such as Engineering Admin Assistant, automated design review, and simulation workflow automation, from feasibility and POC through production.
- Translate engineering SME needs into technical designs and guide internal engineers and external partners through design reviews, code reviews and release readiness.
- Hire, mentor and technically lead agent developers, engineering integration/MCP engineers, knowledge/data engineers and AI software engineers as the portfolio scales.
# Required Qualifications
- Bachelor’s or Master’s degree in computer science, software engineering, engineering, AI or related discipline; typically 12+ years of relevant software/architecture experience.
- Demonstrated hands-on delivery of production generative AI and agentic AI solutions, including LLM tool use, orchestration, retrieval, evaluation and runtime reliability.
- Strong Python/backend development and enterprise API/integration experience; practical MCP/server-tool integration experience or equivalent expertise.
- Meaningful engineering applications knowledge across at least two of CAD, PLM, CAE/simulation, engineering requirements or NPD workflows.
- Experience with enterprise architecture, cloud, identity and access control, DevSecOps, deployment operations and technical risk assessment.
- Ability to challenge vendors at implementation depth and lead technical teams across internal stakeholders and partners.
# Preferred Qualifications
- Experience with PTC Creo/Windchill, Ansys, CoLab, Synera or comparable industrial engineering ecosystems.
- Knowledge of ontology design, knowledge graphs, GraphRAG, vector search, semantic data models and engineering data lineage.
- Experience with LangGraph, Semantic Kernel, Amazon Bedrock or equivalent platforms; Databricks/OneData integration; event-driven systems and cloud-native deployments.
- Exposure to geometric feature analysis, deterministic engineering checks, solver automation, surrogate models, digital thread and automated design validation.
- Experience designing technical standards and scaling reusable AI solution components across multiple business units.
# First-Year Outcomes / Success Measures
- Approved engineering AI reference architecture and explicit central-IT-versus-engineering ownership model.
- Reusable secure engineering context, agent and MCP/API patterns adopted by multiple use cases.
- Production-ready architecture and measurable quality controls for priority Assistant, CoLab and Synera integrations.
- Engineering AI vendor-review standards, technical acceptance checklists and documented support/ownership handovers.
- Sustainable internal development capability, engineering AI operations model and reduced dependence on single implementation partners."
Skills
- Azure AI Services
- LLM
- Retrieval-Augmented Generation
- Databricks
- Model Context Protocol
- AWS
- Generative AI
- Python
- LangGraph
- Semantic Kernel
- Bedrock