As a Principal Software Engineer at JPMorganChase within the Corporate Sector – AI/ML & Data Platforms for LLM Suite, you will lead a specialized technical area, driving impact across teams, technologies, and projects. In this role, you will leverage your deep knowledge of machine learning, software engineering, and product management to spearhead multiple complex ML projects and initiatives, serving as the primary decision-maker and a catalyst for innovation and solution delivery. LLM Suite is JPMorganChase’s premier internally built AI tool leveraged by +250k employees for everything from individual productivity to larger scale, business solutions. 

You will be responsible for hiring, leading, and mentoring a team of Machine Learning and Software Engineers, focusing on best practices in ML engineering, with the goal of elevating team performance to produce high-quality, scalable ML solutions with operational excellence.

Job Responsibilities:

• Design and implement agentic AI reference architectures, including orchestration, retrieval, memory, guardrails, and evaluation harnesses.
• Write production-quality Python code (PyTorch or TensorFlow as needed) and review critical-path code 
• Create reusable components for prompt management, evaluators, safety filters, connectors, embeddings pipelines, and memory stores 
• Build and operate LLM-powered APIs and microservices integrated into advisor, client, and internal workflows 
• Own the end-to-end ML lifecycle: experimentation, CI/CD, automated testing, monitoring, drift detection, versioning, and rollback 
• Optimize inference for latency, throughput, caching, batching, model selection, and cost per inference 
• Partner with data teams on structured and unstructured data pipelines, document ingestion, metadata, and access controls 
• Set engineering standards for agentic AI systems and lead design reviews 
• Influence roadmap and priorities through technical insight and delivery 
• Architects and governs agentic AI-enabled engineering workflows (using enterprise-authorized tools within the work environment) to improve delivery speed, code quality, and operational outcomes at scale (e.g., AI-driven PR review assistance, test generation/maintenance, release readiness checks, incident triage and root-cause acceleration), while defining guardrails for validation, security, resiliency, and reuse across teams.
• Applies knowledge of tools within the Software Development Life Cycle toolchain, including enterprise-authorized AI-assisted development and automation capabilities, to improve the value realized by automation at scale. 

Required Qualifications, Capabilities, and Skills: 

• Formal training or certification on software engineering concepts and 7+ years applied experience 
• Strong Python engineering skills; experience with PyTorch or TensorFlow 
• Expertise working with Vector storage systems and designing memory for Agents 
• Expertise developing long running agents that run autonomously using tools, skills and human in the loop 
• Proven experience deploying LLM-backed services to production (APIs, microservices) 
• Deep MLOps experience, including CI/CD, monitoring, incident response, and model governance 
• Cloud-native AI deployment experience (AWS or Azure), with cost and performance optimization 
• Demonstrated commitment to responsible AI practices and operational excellence 
• Strong communication and collaboration skills, working across product, risk, legal, and compliance teams 
• Demonstrated experience designing and leading adoption of agentic AI-enabled development practices (using enterprise-authorized tools within the work environment) across teams, including setting standards for human-in-the-loop validation, auditability/traceability of changes, and secure handling of sensitive data. 
• Strong understanding of responsible AI use and control expectations in engineering workflows, including security/resiliency implications, data sensitivity, and risk-based governance; ability to influence senior technical leaders on safe scaling patterns and reuse.  

Preferred Qualifications, Capabilities, and Skills: 

• Experience with fine-tuning, adapters, or custom evaluation frameworks 
• Background operating AI systems in regulated environments (finance, healthcare, etc.) 
• Experience with prompt engineering and LLM orchestration 
• Knowledge of safety filters, audit logging, and explainability in production systems 
• Experience mentoring senior engineers and leading architecture discussions 
• Demonstrated ability to influence technical roadmaps and priorities