Agentic AI Engineer

Texas Instruments•Richardson, TX

About The Position

Texas Instruments is transforming semiconductor manufacturing through AI. This role sits within the Smart Manufacturing Automation (SMA) organization. You will design, build, and operate the agentic AI infrastructure that powers factory intelligence across TI's global fab and assembly/test operations to connect large language models to live manufacturing data systems and enabling rapid decision support at scale.

Requirements

Bachelor's degree in Computer Science, Software Engineering, Electrical Engineering, or a related technical field.
4+ years of software engineering experience, with at least 2 years focused on AI/ML systems or LLM application development.
Proficiency in Python and experience containerizing applications with Docker.
Hands-on experience building or integrating with REST API backends and asynchronous service architectures.
Strong communication skills — able to translate complex AI architecture decisions for non-technical manufacturing stakeholders.

Nice To Haves

Experience with multi-agent AI frameworks, agent orchestration patterns, or the MCP (Model Context Protocol) specification.
Familiarity with LiteLLM, Open Web UI, or similar LLM proxy/routing platforms.
Experience deploying workloads on Kubernetes (K8s) or cloud-adjacent enterprise platforms.
Working knowledge of graph databases (Neo4j) and vector search systems (Vectara, pgvector, or equivalent).
Prior exposure to semiconductor or discrete manufacturing data systems (MES, FDC, SPC, SCADA, APC) is a strong plus.
Experience with workflow automation tools (e.g. Airflow) and CI/CD pipelines (Bitbucket, Jenkins, or equivalent).
Master's degree or equivalent industrial AI research experience.

Responsibilities

Architect and deliver multi-agent AI systems using the A2A (Agent-to-Agent) protocol, including orchestrator and sub-agent topologies that span multiple factory data sources.
Build and maintain MCP (Model Context Protocol) servers in Python, containerized with Docker and deployed on VMs and Kubernetes clusters; register agents and MCP servers.
Integrate LLM inference into factory workflows; manage LiteLLM project credentials, budgets, and routing configurations.
Develop agent tools that query manufacturing databases (MES, FDC, APC, OEE, etc.) and expose clean interfaces for downstream AI consumption.
Design, evolve, and influence the Agent Delivery Framework.
Establish and document agentic software development best practices; create reusable agent templates adopted across business teams.
Build and maintain Knowledge Graph and RAG systems (Neo4j, Vectara) to enable document and parametric data retrieval across thousands of manufacturing documents and records.
Collaborate with multiple departments, domain architects, and factory engineers to identify high ROI agent use cases, prioritize delivery, and ensure agents meet security and authentication requirements.
Present architecture roadmaps and live agent demos to peers and senior manufacturing leadership.
Contribute to cross-domain AI access and guardrails governance strategy.