Sr Lead Software Engineer

JPMorganChase•Jersey City, NJ

About The Position

As a Senior Lead Software Engineer at JPMorgan Chase within the Corporate Technology Data Strategy & Architecture organization, you will be an integral part of an agile team that enhances, builds, and delivers trusted technology products securely, reliably, and at scale. You will apply deep technical expertise and problem-solving skills to address challenges across multiple technologies and applications, driving significant business impact. The role leads the design and implementation of complex software features and develops production-grade data-intensive applications and AI systems. This includes agentic AI workflows and LLM-based applications, with responsibility for operational observability, evaluation, safety, and stability in regulated financial services environments. You will also mentor engineers, contribute to firmwide engineering practices, and promote governed, measurable use of approved AI-assisted development and automation tools across teams and the software development lifecycle.

Requirements

Formal training or certification in software engineering concepts and at least 5 years of applied experience.
Hands-on experience building and shipping LLM-based applications and agentic systems with tool use, memory, and multi-step reasoning in production environments.
Advanced proficiency in one or more programming languages, particularly Python and/or Java.
Deep experience with large-scale data processing, microservices, API design, and event streaming such as Kafka.
Working knowledge of relational and NoSQL databases, vector stores, and data lake architectures.
Experience with caching technologies such as Redis or MemCached; observability tools such as Dynatrace, Splunk, or Grafana; and orchestration frameworks such as Airflow or Temporal.
Proficiency in CI/CD, test-driven development, automation, and all aspects of the Software Development Lifecycle.
Strong understanding of agile methodologies, application resiliency, and security best practices.
Practical cloud-native engineering experience with AWS, Azure, or GCP.
Demonstrated experience leading effective use of enterprise-authorized AI-assisted software development tools, such as for coding, code review, test acceleration, or troubleshooting, 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 adherence to resiliency and security expectations.
Experience coaching senior engineers or leads on compliant AI usage patterns and controls.

Nice To Haves

Experience with LLM orchestration frameworks.
Hands-on experience with model serving infrastructure or managed endpoints such as AWS Bedrock or Azure OpenAI.
Familiarity with AI evaluation and observability practices, including evaluation frameworks, red-teaming, prompt drift detection, and cost and latency monitoring.
Understanding of agentic design patterns and how to constrain agent autonomy in high-stakes financial workflows.
Experience with modern data platforms such as Databricks or Snowflake.
Hands-on experience with Spark/PySpark and large-scale big data processing.
Knowledge of the financial services industry and its technology systems.
Awareness of AI risk and regulatory considerations relevant to AI use in financial decision-making.

Responsibilities

Develop secure, high-quality production code for data-intensive applications and platforms; review and debug code written by others.
Lead end-to-end design and implementation of complex software features, from requirements through deployment and operational stability.
Drive technical decisions affecting application design, functionality, performance, and reliability.
Build and maintain agentic AI systems, including multi-agent workflows, tool-use integrations, and human-in-the-loop controls suitable for regulated financial services environments.
Implement LLM-based applications, including RAG pipelines, embedding workflows, vector store integrations, and model serving infrastructure.
Own observability, evaluation, and safety of production AI systems, including prompt monitoring, output validation, cost tracking, and latency optimization.
Identify and execute opportunities to automate remediation of recurring issues and improve operational stability.
Design, develop, and troubleshoot creative software solutions to solve complex and ambiguous problems.
Mentor and coach junior and mid-level engineers, conduct code reviews, and share engineering best practices.
Contribute to firmwide frameworks, tools, and SDLC practices as an engaged member of the engineering community.
Drive adoption and governance of approved AI-assisted engineering practices across teams, using measurable validation standards for secure coding, peer review, and automated testing.
Promote reuse of proven patterns and automation within the SDLC/TLM toolchain, applying approved AI-assisted development and automation capabilities to improve automation at scale.