**Applied AI ML, Senior Associate - LLM Suite Engineering** at JPMorganChase, Wilmington, DE. Design and implement components of scalable AI platforms for enterprise workflows, build production AI systems using agents and skills. Engineer cloud-native services on AWS, optimize model workloads and connect AI capabilities to enterprise platforms. Improve system quality through evaluation and observability signals. Collaborate with teams to deliver resilient, measurable deliverables.
Full Job Description
Location: Wilmington, DE, United States
Join a team building scalable, production-grade AI capabilities that help teams across the firm deliver better outcomes through reliable automation and decision support. You will work end-to-end, from design to implementation and operational readiness, partnering closely with engineering and product stakeholders.
As an Applied AI and Machine Learning Senior Associate at JPMorganChase within LLM Suite Engineering in Enterprise Technology, you will help design and deliver agentic AI platforms and large language model-enabled services for enterprise use cases. You will contribute to architecture decisions, build cloud-native services on AWS, and improve system quality through evaluation and observability. You will help raise engineering standards through strong code reviews, documentation, and collaboration across teams.
Job responsibilities
Design and implement components of scalable, reliable agentic AI platforms for enterprise workflowsBuild production-grade AI systems including agents, skills, memory patterns, guardrails, and tool-use orchestrationImplement retrieval and context-engineering patterns including embeddings, semantic search, grounding, summarization, and prompt/version managementEngineer cloud-native services on AWS using containers, serverless compute, and event-driven messaging patternsOptimize latency, throughput, scalability, caching, context efficiency, and cost across large language model workloadsDevelop secure, reusable APIs and integrations that connect AI capabilities to enterprise platforms and workflowsImplement evaluation, experimentation, regression testing, and observability signals to improve quality and agent behavior over timePartner with product, platform, and engineering teams to translate requirements into resilient, measurable deliverablesContribute to technical standards and code quality through design reviews, documentation, and peer code reviewsRequired qualifications, capabilities and skills
Formal training or certification on applied AI and machine learning concepts and 3+ years applied experienceHands-on experience building and operating production large language model applications, including agentic patterns and tool integrationsStrong software engineering skills with experience delivering cloud-native services on AWS using containers and serverless architecturesExperience with retrieval-augmented generation approaches, including embeddings and semantic search, and practical context engineeringProficiency building APIs and service integrations with strong attention to reliability, security, and performanceExperience establishing or contributing to evaluation, testing, and monitoring practices for AI system quality and reliabilityAbility to troubleshoot complex issues across distributed systems, including asynchronous workflows and event-driven architecturesStrong collaboration skills with the ability to communicate technical decisions and trade-offs clearly to partnersPreferred qualifications, capabilities and skills
Experience deploying and operating workloads on Kubernetes-based platforms and container orchestration patternsExperience with experimentation frameworks and automated regression testing for large language model qualityFamiliarity with large language model cost governance and performance optimization techniques (for example, caching and context efficiency)Experience implementing guardrail patterns that support safe, reliable AI behavior in productionExperience building reusable platform components and reference implementations adopted by multiple teams Build enterprise-grade agentic AI platforms and retrieval systems to deliver reliable large language model experiences at scale. 
