About the role
from listingThe Enterprise Technology Services organization partners with every part of the American Express business to power the company’s growth and innovation with trust and efficiency, and drive competitive differentiation with speed. We support the delivery and operations of technology, digital, and data capabilities, platforms, and services globally. Specifically, our team is responsible for the company’s technology engineering, architecture, and infrastructure, providing 24x7 support to ensure an uninterrupted, high-quality experience for customers and colleagues.
We also provide product management for core enterprise platforms, and lead technology risk and information security, enterprise data governance and platforms, digital product and design, and enterprise AI platforms on behalf of the company.
The Inference Engineer is responsible for independently designing, optimizing, and operating scalable production inference services that enable enterprise AI and machine learning solutions. This role partners with stakeholders to translate business and technical requirements into reliable model-serving capabilities, build efficient integration patterns and data pipelines, and ensure solutions meet established enterprise architecture standards for performance, reliability, observability, compliance, and production readiness.
Mentors junior AI Engineers and cross-functional team of colleagues, fostering a culture of excellence and innovation
Integrates AI models into production systems in collaboration with cross-functional teams, ensuring effective integration into existing production systems
Maintains strict adherence to model governance, security, and compliance standards
Collaborates with engineers to deliver scalable AI solutions by integrating models that meet both technical and business requirements
Translates business requirements into AI-driven technical solutions, ensuring that business needs are converted into actionable models and algorithms
Creates end-to-end machine learning operations pipelines for scalable model deployment, facilitating seamless deployment, monitoring, and maintenance of AI models
Collaborates and co-creates effectively with teams in product and the business to align technology initiatives with business objectives
Designs and operates scalable production AI systems, integrating ML models, LLMs, and intelligent services across multiple components
Ensures AI systems adhere to enterprise standards for reliability, safety, explainability, observability, and compliance, mentoring others on best practices
Designs and operates scalable inference services, including performance, reliability, observability, and production readiness.
Evaluates serving approaches and optimizes latency, throughput, accelerator utilization, and cost for assigned workloads.
Partners across platform, infrastructure, security, evaluation, and application teams and mentors less-experienced engineers.
Education and Knowledge
Bachelor's degree in Computer Science, Machine Learning, Data Science, and/or comparable experience; advanced degree preferred
Advanced knowledge of machine learning techniques and performance optimization
Strong understanding of AI system architectures including LLM ecosystems, retrieval systems, orchestration frameworks, and evaluation methodologies
Strong knowledge of production model serving, inference optimization, GPU fundamentals, Kubernetes, APIs, and distributed systems.
Ability to evaluate technical alternatives and make sound service-level design decisions within established architecture.
Work Experience
5+ years software development experience, including hands-on experience in machine learning, AI technologies, and Agentic AI solutions.
Experience in working with large language models (LLMs), especially GPT-3.5/4 or similar AI models
Experience in languages such as Python, R, Java, or C++
Experience in deploying AI models and pipelines using machine learning operations tools
Experience in machine learning algorithms and experience applying them to real-world problems
Experience in continuous integration/continuous deployment pipelines and containerized deployments
Experience delivering end-to-end AI systems in production, including design and operational ownership
Experience with distributed systems design, scalable APIs, and cloud-native AI infrastructure, including monitoring and optimization
Advanced expertise in a technical domain and moderate expertise in a new, different technical domain
Demonstrated experience independently building and operating production inference services.
Experience with model-serving frameworks, containerized GPU workloads, and performance or reliability optimization.
Employment eligibility to work with American Express in the United States is required as the company will not pursue visa sponsorship for these positions.