Senior Lead Software Engineer - Agentic AI/Java/Python
On-sitePlano, Texas, United States
Plano, Texas, United StatesOn-siteFull TimeSenior LevelFinancial ServicesEnterprise
Full TimeSenior LevelEnterpriseFinancial Services
Job Summary
Design and build critical technology solutions for Chase AI components, including Chase Agent and Domain Agents, by executing software development, troubleshooting, and creating secure production code. Produce architecture artifacts for complex applications while gathering data insights to drive continuous improvement in coding hygiene and system design. Collaborate with cross-functional teams to deliver end-to-end solutions that ensure compliance with security, privacy, and regulatory requirements. Lead team adoption of enterprise-authorized AI-assisted engineering practices to improve code quality and delivery speed.
Required Qualifications
- 5+ years of software engineering experience, with 2+ years building complex scalable applications or agentic systems
- Hands-on experience building agentic systems using LLMs/SLMs
- Experience setting up and maintaining MCP servers and building MCP-compatible tools/adapters
- Proficient in coding in one or more languages: Java and/or Python
- Proficiency building production services with either Spring AI or the Spring ecosystem (Spring Boot, Spring Security, Spring Cloud), or Python (FastAPI/Flask), with typed contracts, testing, and packaging
- Solid AWS background with working knowledge of ECS or EKS, containerization (Docker), and CI/CD (GitHub Actions/Jenkins/CodeBuild)
- Strong API design skills (REST/OpenAPI; gRPC and familiarity with observability stacks (e.g., Splunk, CloudWatch, Prometheus/Grafana, OpenTelemetry)
- Practical understanding of LLM patterns: function calling/tools, RAG, prompt management, context windows, token budgeting, and safety guardrails
- Strong testing culture: unit/integration tests, load tests, and evaluation datasets for agents
- Demonstrated experience leading effective use of approved AI-assisted software development tools (e.g., for coding, code review, test acceleration, troubleshooting) with the ability to set team expectations for validating AI outputs for correctness, performance, and security
- Strong understanding of responsible AI use in engineering workflows, including data sensitivity considerations, secure handling of inputs/outputs, and adherence to resiliency and security expectations; experience coaching engineers on safe, compliant adoption within delivery practices
Desired Qualifications
- Expertise with distributed orchestration patterns for LLM applications (graph-based flows, retries, fallbacks, guardrails) and secure integration with enterprise tools and data
- Experience with safe rollout strategies (shadowing, A/B testing, progressive exposure), human-in-the-loop review, and continuous evaluation for quality and safety, including canary rollouts
- Knowledge of API gateways, service mesh, and multi-region high availability and disaster recovery for mission-critical services
- Familiarity with data privacy, security best practices, and regulatory compliance in financial services
- Experience with performance optimization, scalability, and reliability engineering for large-scale systems
- Ability to evaluate and integrate third-party tools, libraries, and frameworks to accelerate development
- Demonstrated leadership in technical communities, open source contributions, or industry forums
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.