AI Engineer III - Agentic AI
American Express · Phoenix, AZ · 1 wk ago
HybridInformation TechnologyFull-time
About the role
Joining Amex Tech means discovering and shaping your contribution to something big. Here, you can work alongside talented tech teams and build a unique career with the Powerful Backing of American Express.
Responsibilities
- Contribute to the design and implementation of LLM-powered and agentic product features.
- Build and extend agentic AI workflows that reason over context, call tools, and perform actions under guidance from senior engineers.
- Help implement and maintain retrieval-augmented generation (RAG) pipelines over financial data, with an emphasis on correctness and safety.
- Contribute to shared AI infrastructure such as LLM services, orchestration components, and evaluation or monitoring tooling.
- Participate in operating AI systems in production, including monitoring, debugging, and improving reliability and performance.
- Collaborate closely with product and design partners, learning to translate customer needs into technical solutions.
Qualifications
- 4+ years of professional software engineering experience.
- Solid engineering fundamentals in at least one backend language (Python, Go, or TypeScript).
- Familiarity with APIs, basic cloud concepts, and modern development practices.
- Interest in agentic AI systems, autonomy, and AI-assisted development workflows.
- Comfort working in collaborative, cross-functional teams.
- A strong customer mindset and curiosity about real-world problem solving.
Preferred Qualifications
- Exposure to LLM tooling, prompt engineering, RAG, or agent frameworks through work, coursework, or personal projects.
- Internship or early-career experience in fintech or other regulated environments.
- Contributions to open-source projects, hackathons, or side projects related to AI or developer tooling.
Pay
Ultimately, in determining your pay, we’ll consider your location, experience, and other job-related factors.
Schedule
Depending on role and business needs, colleagues will either work onsite, in a hybrid model (combination of in-office and virtual days) or fully virtually.