C

Caterpillar

Makes heavy machinery, engines and gas turbines

Autonomy Operation Agent Engineer

AI Application EngineeringConfirmed live in the last 24 hours
Full-timeNo salary listedIn-person

About the Job

Requirements

  • A master's degree or higher in computer science, artificial intelligence, software engineering, automation, data science, or a related major is required.
  • Have a solid programming foundation, familiarity with Python, and good software engineering and system development abilities.
  • Understand large language model fundamentals and have knowledge or project experience related to large language models, retrieval-augmented generation, prompt engineering, function calling, or tool calling.
  • Understand Agent architecture and mechanisms, including task planning, context management, knowledge retrieval, tool calling, and workflow orchestration.
  • Have product and business understanding, and be able to translate real user problems and ambiguous needs into implementable, verifiable intelligent applications.
  • Have systems thinking and engineering awareness, with attention to production reliability, maintainability, security boundaries, and user value.
  • Be willing to learn and understand the production and operations processes of autonomous mining.

Responsibilities

  • Plan and evolve the overall application technology and product portfolio for autonomous-site Agents, initially focusing on Agents for autonomous-driving back-office operations, and define product portfolios, scenario roadmaps, capability boundaries, and core technical principles before expanding to broader autonomous-site scenarios.
  • Design and develop specialized Agents for different user roles and business scenarios, initially covering operations analysis, anomaly diagnosis, knowledge services, and site management, with planned expansion to maintenance support, engineering efficiency, and other high-value scenarios.
  • Build Agent capabilities for scenario understanding, business reasoning, task decomposition, and multi-step execution using large language models, retrieval-augmented generation, tool calling, context management, memory, planning, and Agent workflows.
  • Expose existing autonomous-site system capabilities as tools and services callable by Agents, connecting operational intelligence, dispatch, digital twins, equipment and site status, knowledge systems, and other back-office services so Agents can reuse deterministic domain capabilities.
  • Develop cross-system and cross-business-domain Agent workflows that retrieve information, orchestrate tasks, track status, and provide results across multiple back-office systems, data sources, and business processes.
  • Explore multi-Agent collaboration, including task decomposition, capability discovery, collaboration, information sharing, and result aggregation among specialized Agents.
  • Design human-Agent collaboration and control mechanisms supporting recommendations, confirmation, approval, controlled execution, and human takeover according to task risk and business impact.
  • Establish evaluation and continuous-improvement loops for the Agent application layer, optimizing task completion quality, factual accuracy, tool-call correctness, workflow success rate, reliability, response efficiency, and user value.
  • Collaborate with AI infrastructure and Agent operations, intelligent operations, digital twin, collaboration-system, and other domain teams; define application- and infrastructure-layer boundaries; reuse shared model access, knowledge retrieval, runtime, evaluation, observability, and governance capabilities to build reliable Agent applications.
  • Explore the technical path for evolving Agent technology toward autonomous site operations, advancing from knowledge assistance and decision support toward controlled task execution, multi-Agent collaboration, and greater autonomy subject to defined objectives, permissions, safety boundaries, validation, and human-takeover conditions.

Desired Qualifications

  • Project experience related to large language models, retrieval-augmented generation, Agents, multi-Agent systems, or Agent workflows.
  • Familiarity with Semantic Kernel, LangGraph, AutoGen, or similar Agent development frameworks.
  • Experience with vector databases, knowledge graphs, enterprise search, natural-language querying of data, or knowledge management.
  • Experience with back-end services, application programming interfaces, microservices, workflow engines, or enterprise application integration.
  • Project experience in robotics, autonomous driving, industrial internet, mining, logistics, production operations, or complex industrial systems.
  • Ability to demonstrate an end-to-end artificial intelligence product or Agent project spanning user problem definition, Agent design, engineering implementation, and evaluation.

About the Company

Caterpillar

Makes heavy machinery, engines and gas turbines

Caterpillar makes construction and mining machines, diesel and natural gas engines, industrial gas turbines and locomotives for contractors, mines, energy companies and data center builders. It is the world's largest maker of construction and mining equipment, and its yellow Cat bulldozers and excavators work in nearly every country. Customers buy or rent machines through independent Cat dealers, while its engines and turbines generate electricity and push natural gas through pipelines. Caterpillar earns money from equipment sales and from the parts and repairs that dealers supply over a machine's working life. It was formed in 1925 when California's Holt and Best tractor companies merged, and it is based in Irving, Texas.

Company size
10,001+
Company stage
IPO
Headquarters
Irving, TX
Founded
1925

Recently Posted Jobs

Explore more opportunities at Caterpillar

See more jobs