We are looking for engineers to build production-grade agentic AI systems that transform customer service experience across servicing channels. This role focuses on delivering measurable customer and operational outcomes through intelligent automation—not just building models.
At American Express, our culture is built on a 175-year history of innovation, shared values and Leadership Behaviors, and an unwavering commitment to back our customers, communities, and colleagues. From delivering differentiated products to providing world-class customer service, we operate with a strong risk mindset, ensuring we continue to uphold our brand promise of trust, security, and service.
As part of Team Amex, you’ll experience our powerful backing with comprehensive support for your holistic well-being and many opportunities to learn new skills, develop as a leader, and grow your career. Here, your voice and ideas matter, your work makes an impact, and together, you will help us define the future of American Express.
Responsibilities:
- Design, build, and deploy LLM-powered and agentic AI systems for real-time customer interactions across voice, chat, and messaging channels.
- Develop intelligent agents that:
- Understand customer intent
- Reason over context (interaction history, sentiment, policies)
- Invoke enterprise tools (CRM, knowledge bases, ticketing systems)
- Execute actions in real time and recover gracefully from failures
- Architect and implement scalable RAG pipelines over customer data, knowledge bases, and operational systems, ensuring:
- High accuracy and low hallucination rates
- Compliance and auditability
- Strong data privacy and PII handling
- Build and extend shared AI platforms, including:
- Conversational AI services
- Agent orchestration frameworks
- Real-time agent assist systems
- Evaluation, monitoring, and observability tooling
- Own end-to-end system performance, including:
- Reliability and fault tolerance
- Low-latency response constraints (real-time systems)
- Cost efficiency at scale
- Partner closely with product, operations, and CX design teams to deliver measurable outcomes such as:
- Reduced resolution time
- Increased containment
- Improved CSAT
- Enhanced agent productivity
Technical Environment
We operate in a modern, enterprise-scale environment focused on real-time, customer-facing AI systems. Strong fundamentals matter more than exact tool matching.
Core Engineering Stack
- Languages: Python, Go, TypeScript
- Cloud & Infrastructure: AWS and/or GCP, Kubernetes
- APIs: REST, gRPC
- Distributed Systems: Event-driven architectures (e.g., Kafka)
- Datastores: Postgres, MongoDB
- Vector Databases: Pinecone, Weaviate, FAISS
- Async Processing: Celery, Kafka
- Deployment: FastAPI, Docker, serverless
- Observability: LangSmith, Weights & Biases, Helicone
Agentic AI & Machine Learning (CX Focus)
- Hands-on experience integrating commercial and open-source LLMs into production workflows
- Experience building:
- Agent orchestration systems for multi-step interaction handling
- RAG pipelines over structured and unstructured enterprise data
- Semantic search systems using vector databases
- Evaluation frameworks (accuracy, hallucination, compliance, CX metrics)
- Strong practices in:
- Conversation state management
- Schema and tool interface design
- Guardrails, validation, and safe execution in regulated environments
AI-Assisted Development
- Fluency with AI-assisted development workflows (code generation, testing, evaluation, iteration)
- Ability to use these tools effectively while maintaining production-grade engineering standards
System Expectations
All systems must meet enterprise standards for:
- Reliability in high-volume, real-time environments
- Security and data privacy (including PII handling)
- Auditability of automated decisions and interactions
- Responsible AI deployment in regulated customer contexts
Qualifications:
Required Qualifications
- 5+ years of software engineering experience, including production systems involving LLMs, conversational AI, or applied ML
- Proven track record of building and deploying AI-powered systems in customer-facing or operational environments (e.g., chatbots, agent assist, automation)
- Strong engineering fundamentals across:
- Backend systems
- APIs
- Data pipelines
- Cloud infrastructure
- Hands-on experience with modern LLM tooling and agentic architectures
- Strong ownership mindset and ability to operate in ambiguous problem spaces
- Product-oriented thinking with focus on customer experience and operational impact
Preferred Qualifications
- Experience in regulated industries (financial services, healthcare, telecom)
- Experience in high-growth or transformation environments
- Track record of deploying systems that directly impact customer interactions at scale
- Contributions to open-source projects in AI, conversational systems, or developer tooling
