Lead Software Engineer Python GenAI

JPMorganChase•Wilmington, NC

About The Position

As a Lead Software Engineer in Python GenAI at JPMorgan Chase, within the Corporate Sector’s Model Delivery and Platform Engineering team, you will contribute to an agile team building and delivering secure, stable, and scalable technology products. You will develop and operate solutions across technical areas that support the firm’s business objectives, with a focus on automation, application risk and compliance, security and data accountability, and production reliability. The role leads the use of automation, including LLMs and agents, to reduce manual operational work and streamline AO workstream remediations. It also involves coordinating execution across product and engineering teams, operating resilient production services, advancing site reliability practices, and using data-driven analysis to improve application and platform service levels. You will promote enterprise-authorized AI-assisted engineering practices, establish validation standards for AI-generated outputs, and share knowledge across the organization.

Requirements

Formal training or certification in software engineering concepts and at least 5 years of applied experience.
Advanced development experience in Java or Python and excellent debugging and troubleshooting skills for complex production issues.
Hands-on experience with AWS or other cloud platforms and container platforms or orchestration, such as Docker, Kubernetes, or ECS.
Experience building scalable data processing and Big Data/ETL pipelines, such as Hortonworks or AWS-based solutions.
Working knowledge of core infrastructure, including routers, load balancers, compute, storage, networks, and cloud products, with the ability to troubleshoot common networking technologies and issues.
Deep proficiency in reliability, scalability, performance, security, enterprise architecture, and toil reduction, including the ability to implement SRE practices in applications and platforms.
Proficiency in white-box and black-box monitoring, SLO alerting, and telemetry collection using tools such as Grafana, Dynatrace, Prometheus, Datadog, or Splunk.
Ability to learn and evaluate new technologies, teach languages to others, and collaborate across levels and stakeholder groups.
Strong foundations in software applications and processes, emerging depth in a discipline, and ability to solve complex data structures and algorithms problems.
Demonstrated experience leading effective use of approved AI-assisted software development tools for activities such as coding, code review, test acceleration, and troubleshooting, and setting team expectations for validating outputs for correctness, performance, and security.
Strong understanding of responsible AI use in engineering workflows, including data sensitivity, secure handling of inputs and outputs, and adherence to resiliency and security expectations; experience coaching engineers on safe, compliant adoption.

Nice To Haves

Current AWS credential, such as Cloud Practitioner, Solutions Architect, SysOps Administrator, or Developer, demonstrating working knowledge of core AWS services, cloud architecture patterns, IAM and security fundamentals, VPC and networking basics, monitoring and logging, and cost awareness.
Recognized automation or DevOps credential, such as in Kubernetes or containers, CI/CD, Infrastructure as Code, or site reliability.

Responsibilities

Design, code, test, and deliver automation, including LLMs and agents, to reduce manual operational work and streamline AO workstream remediations.
Own application risk, controls, and compliance, including adherence to firm standards, Technology Lifecycle Management, and closure of issues and findings through remediation and evidence management.
Ensure application security and data accountability, including authentication and authorization, vulnerability and certificate hygiene, data registration and classification, and compliant storage, retention, and disposal.
Coordinate product and engineering teams to prioritize and execute AO workstreams, influence and coach teams, and align execution across large developer communities.
Operate production services end-to-end by implementing monitoring, logging, and anomaly detection; maintaining secure network configurations and least privilege; and leading or supporting incident, problem, change, recovery, and resiliency practices.
Champion site reliability culture and practices and exert technical influence across the team.
Lead initiatives to improve application and platform reliability and stability using data-driven analytics.
Collaborate with team members to identify service level indicators and with stakeholders to establish service level objectives and error budgets.
Document and share knowledge through internal forums and communities of practice.
Drive adoption of enterprise-authorized AI-assisted engineering practices to improve code quality, delivery speed, and operational outcomes.
Establish consistent validation standards for AI-assisted work, including secure coding, peer review, and automated testing, and promote reuse of effective patterns.
Apply knowledge of the Software Development Life Cycle toolchain, including authorized AI-assisted development and automation capabilities, to improve the value realized by automation.