Lead Software Engineer - Java or Python, Agentic AI

JPMorganChase•Jersey City, NJ

About The Position

As a Lead Software Engineer on JPMorgan Chase’s Commercial & Investment Bank Digital Channel team, you will build autonomous agent capabilities that can plan, execute, validate, and submit code changes in bulk. The role focuses on evaluation harnesses, PR-provenance controls, CI/CD integrations, and operational readiness to scale machine-authored changes safely across runtime upgrades, framework migrations, security remediation, and standards adoption. You will design and integrate AI-driven remediation workflows into enterprise CI/CD pipelines and build and operate an evaluation harness to demonstrate agent quality and delivery readiness at scale. Under the Sr Lead’s design, you will implement the PR-provenance contract end to end and own specific evaluation-harness subsystems, while co-owning reliability and observability. You will also support the Standards and Tooling pillars by integrating rollout checks into the harness and CI/CD flow, and instrument value, adoption, and operational metrics. The role includes driving team adoption of enterprise-authorized AI-assisted engineering practices and establishing consistent validation standards for secure coding, peer review, and automated testing. It applies software development lifecycle tools, AI-assisted development, and automation to improve code quality, delivery speed, and operational outcomes.

Requirements

Formal training or certification in software engineering concepts and at least 5 years of applied experience developing, debugging, and maintaining code in a corporate environment.
Experience with modern programming, scripting, and database-query languages such as Java, Python, shell scripting, SQL, PostgreSQL, Oracle, SQL Server, or MySQL.
Experience contributing to a CI/CD, DevOps, or release-engineering platform, including release pipelines, build and test automation, signed-attestation systems, deployment controls, or audit-trail tooling.
Strong hands-on experience with Java, Spring Boot, Kafka, API development, Python, and shell scripting for automation services, test harnesses, evaluation tooling, pipeline instrumentation, and operational tooling.
Experience with relevant development and testing frameworks and tools such as REST APIs, OpenAPI/Swagger, Maven, Gradle, JUnit, Mockito, Selenium, Playwright, Cucumber, pytest, or SonarQube.
Hands-on experience using enterprise-authorized AI-assisted software development tools for coding, test creation, troubleshooting, or documentation, and ability to critically evaluate and refine AI-generated outputs for correctness, performance, and security.
Understanding of responsible AI use in engineering workflows, including data sensitivity, secure input and output handling, resiliency and security expectations, and the ability to guide peers on safe usage.
Experience with responsible-AI controls and practices such as secure prompt and input handling, AI-output validation checklists, model-output review workflows, and audit-evidence capture.
Hands-on experience with AWS or Azure, Kubernetes-based deployment automation, Docker, Helm, SQL databases, artifact repositories, secrets management, and controlled enterprise deployment environments.
Experience with deployment and release controls such as HashiCorp Vault, AWS Secrets Manager, Azure Key Vault, container registries, blue/green deployment, canary releases, rollback automation, release gates, or environment-promotion workflows.
Ability to operate a subsystem end to end under senior design direction, including implementation, deployment, observability, alert response, production support, runbook improvement, and iteration based on quality and reliability signals.
Experience with observability and reliability tools such as Prometheus, Grafana, Splunk, ELK/OpenSearch, OpenTelemetry, Datadog, or AppDynamics.
Working understanding of Git internals, branching workflows, PR and merge tooling, repository governance, commit signing, and large-scale change orchestration.
Experience with source-control and governance tools or controls such as Git, Bitbucket, GitHub, GitLab, branch protections, signed commits, PR approval workflows, dependency scanning, Checkmarx, Snyk, Black Duck, or Fortify.
Demonstrated experience leading effective use of approved AI-assisted software development tools and setting team expectations for validating AI 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 resiliency and security expectations; experience coaching engineers on safe, compliant adoption.

Nice To Haves

Formal training or certification in software engineering, AI/ML engineering, or cloud-native engineering, with experience applying agent-based systems or automation in enterprise delivery.
Proficiency in Python, Java, or similar languages, with exposure to model-evaluation tooling or ML frameworks such as TensorFlow, PyTorch, Scikit-learn, or equivalent platforms.
Experience automating infrastructure-as-code development or remediation using AI/ML-assisted workflows, including Terraform, Ansible, CloudFormation, or equivalent enterprise IaC frameworks.
Deep experience with observability automation and reliability analysis using Prometheus, Grafana, ELK/OpenSearch, OpenTelemetry, or equivalent enterprise monitoring platforms.
Excellent problem-solving, communication, and collaboration skills, with experience partnering across engineering, security, platform, SRE, and application-owner teams.

Responsibilities

Design and integrate AI-driven remediation workflows into enterprise CI/CD pipelines, including triggers, build and test gates, deployment-readiness checks, failure handling, and evidence capture.
Build and operate an evaluation harness that measures agent quality and delivery readiness, including success, regression, PR-merge, pipeline pass, drift-detection, and control-effectiveness signals.
Implement the PR-provenance contract under the Sr Lead’s design, including branch creation, CI/CD hooks, build-verification gates, automated test evidence, audit-trail emission, signed commit and merge attestation, rollback envelope, and operational handoff for failed or blocked runs.
Own evaluation-harness subsystems such as fixture management, replay tooling, regression corpora, quality-signal aggregation, failure triage, runbook maintenance, and day-to-day operational support.
Co-own reliability and observability for the agent harness, including metrics, logs, traces, replay tooling, alerting, dashboards, and failure-pattern analysis.
Contribute to agent-skill design reviews as a subject-matter-capable reviewer of evaluation coverage and provenance implications, escalating audit-control questions to the L5.
Support the Standards and Tooling pillars by wiring rollout of lint rules, template upgrades, quality gates, and migration checks into the evaluation harness and CI/CD flow.
Instrument value, adoption, and operational metrics, including repositories evaluated, provenance-signed PRs, pipeline pass and failure rates, repeat-run reduction, engineering days saved, and audit-evidence completeness.
Drive team adoption of enterprise-authorized AI-assisted engineering practices to improve code quality, delivery speed, and operational outcomes.
Establish consistent validation standards, including secure coding, peer review, and automated testing, and promote reuse of effective patterns across the team.
Apply SDLC toolchain knowledge, including enterprise-authorized AI-assisted development and automation capabilities, to improve the value realized by automation.