Sr AI Engineer I - Global Commercial Services
Senior Software Engineer I – Agentic AI
The Role
As a Senior Software Engineer – Agentic AI, you will be a hands-on engineer within Amex Technology, building and evolving production-grade agentic AI systems that power intelligent customer and enterprise experiences. Working closely with senior engineers, architects, Product, UX, Data Science, and Engineering teams, you will design, implement, and operate scalable, reliable, and secure AI solutions. This role combines strong software engineering fundamentals with experience building AI-powered applications.
Global Commercial Services (GCS) serves millions of business customers around the world, from mom-and-pop shops to Fortune 500 companies. We back businesses so they can do more business, with a mission to be the undisputed leader in financial and membership services - responsibly driving double-digit revenue growth. We do that by offering a diverse range of payment and cashflow tools, from a wide range of traditional card products, to working capital and supply chain financing, to new digital solutions that make it easy for our customers to manage a full range of their financial and payment needs.
What You'll Do
Design, build, test, and operate production-grade agentic AI applications and services.
Contribute to the design and implementation of shared agentic AI capabilities, including:
Agent frameworks and orchestration
Planning, tool use, and memory strategies
Retrieval-Augmented Generation (RAG) pipelines
LLM integration and inference services
Evaluation, observability, and safety tooling
Partner with senior engineers to design scalable, reliable, and maintainable distributed systems.
Participate in technical design discussions and code reviews, helping improve engineering quality across the team.
Collaborate with Product, UX, and cross-functional partners to deliver AI-powered capabilities from concept through production.
Evaluate emerging AI technologies and help incorporate practical improvements into our platform.
Mentor junior engineers and contribute to a collaborative engineering culture.
Technical Environment
We don't hire to a narrow checklist, but successful candidates should be comfortable working in a modern, cloud-native engineering environment with an emphasis on agentic AI.
Core Engineering Stack
Languages: Go, TypeScript, Python
APIs: REST, gRPC, and tRPC
Cloud: AWS and/or GCP
SNS, SQS, Lambda, EKS, API Gateway
Kubernetes
Distributed systems and event-driven architectures (Kafka)
Durable Execution frameworks, like Temporal or DBOS
Orchestration frameworks such as LangGraph, LangChain, Airflow, or similar
Agentic AI and ML
Integrating commercial and open-source LLMs into production applications
Agent and orchestration frameworks such as VercelAI SDK, LangChain, LangGraph, LlamaIndex, etc.
Retrieval-Augmented Generation (RAG) architectures
Embedding Models and Vector Databases
Multi-agent orchestration and agent harness development
Prompt engineering and structured output generation
Model serving, embeddings, and inference tooling
Familiarity with Effect TS library
Schema validation and state management using tools such as Zod (TypeScript)
Emphasize evaluation, observability, safety, and reliability to support AI solutions deployed in a regulated, customer-facing environment.
What We're Looking For
6+ years of experience building large-scale backend or distributed software systems.
Experience developing AI-powered applications using LLMs, agentic workflows, RAG, or modern ML platforms.
Experience building production services using TypeScript, Go, Python or similar languages.
Strong software engineering fundamentals across backend development, APIs, cloud infrastructure, and distributed systems.
Familiarity with cloud platforms, containers, and Kubernetes.
Experience with asynchronous processing, workflow engines, queues, or streaming systems.
Strong problem-solving skills and the ability to work through ambiguous technical challenges.
Excellent collaboration and communication skills, with the ability to work effectively across engineering and product teams.
Passion for learning new technologies and contributing to engineering best practices.
Preferred Qualifications
Experience building AI applications in financial services or other regulated industries.
Experience deploying production LLM or RAG-based systems.
Familiarity with evaluation frameworks, observability, and AI safety practices.
Contributions to open-source software or AI-related projects.
Experience with fine-tuning, model optimization, or inference pipelines is a plus.