Senior Software Engineer (Autonomy Services)
$112,710–$183,140 year
On-siteIrving, Texas, United States
Job Summary
Design, build, test, and deploy backend RESTful API services using Java, Spring Boot, and microservices architecture on AWS. Provide day-to-day technical leadership on complex engineering problems, guide implementation decisions, and mentor engineers through code reviews and pairing. Lead development of new functionality on cross-functional Agile teams while applying AI-assisted and agentic development workflows to accelerate design and implementation. Contribute to application design, technical documentation, and scalable integration patterns while helping identify and resolve root causes for production issues. This role offers the opportunity to influence solution design and raise the engineering bar for the team at Caterpillar's Autonomy Services.
Required Qualifications
- Strong backend engineering capability with Java 17+ and Spring Boot to design and deliver RESTful APIs using microservices principles
- Proven ability to build secure, scalable platform services in a cloud environment such as AWS or Azure
- Experience deploying backend services in cloud-native environments
- Knowledge of AI-assisted and agentic software development workflows
- Ability to review, validate, test, and refine AI-generated code and pull requests for correctness, maintainability, performance, security, and alignment with established engineering standards
- Knowledge of responsible AI usage and secure coding practices in AI-assisted development
- Must be based in Irving, TX (Dallas)
- Domestic relocation assistance is available for this position
- Visa sponsorship is available for this position
- This position requires working onsite five days a week
- Relocation is available for this position
- Visa sponsorship is available for eligible applicants
- Offer of employment is conditioned upon the successful completion of a drug screen
Desired Qualifications
- Experience building production AI agents using Python
- Experience with agent orchestration frameworks such as LangChain or LangGraph
- Experience integration LLMs with external tools, APIs, databases, and retrieval systems
- Experience designing evals, guardrails, and monitoring for agent reliability
- Multi-agent workflow design and memory/context management
- Prompt optimization, latency reduction, and cost control
- MLOps or model deployment experience
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.