Lead GenAI Backend Platform Software Engineer

The Lead GenAI Backend Platform Software Engineer works independently and develops robust, scalable software solutions across the full stack—from cloud infrastructure to backend API integrations, agentic workflows, and MCP servers.

• Design and develop industry-leading solutions that meet defined quality standards, reliability specifications, and strategic objectives.
• Lead the architecture of robust, scalable software solutions, focusing on backend services (FastAPI, Python) and LLM technologies.
• Assist with architecting and developing cloud-native solutions leveraging AWS services, including Bedrock, S3, Fargate, Aurora, Lambda, Step Functions, and emerging technologies.
• Collaborate on system architecture decisions and API design, ensuring secure, performant, and maintainable patterns.
• Demonstrate solid understanding of systems and processes within the job area and recommend improvements.

• Design and implement high-performance, secure APIs using FastAPI and Python, establishing patterns that the team replicates.
• Guide the team in industry-leading practices for software development, code quality, system design, and test automation.
• Apply strong computer science fundamentals, including algorithm design, problem solving, complexity analysis, and data structures.
• Lead the implementation of comprehensive test strategies—including unit testing, integration testing, and end-to-end testing methodologies—championing test-driven development (TDD) practices and automated testing frameworks.

• Assist with implementing and maintaining CI/CD pipelines, fostering a strong Dev Ops culture.
• Identify gaps between system components and designs and deliver solutions that enable team autonomy.
• Take a broad perspective on infrastructure problems, exercising independent judgment in selecting techniques and evaluation criteria to obtain results.
• Develop actionable insights from analyzing software development trends and best practices, communicating integration recommendations to management.

• Mentor and guide less experienced team members in techniques, processes, and best practices for full-stack development, API design, and system architecture.
• Coach and train colleagues in writing clean, maintainable, secure code and thinking systemically about software design.
• Champion collaborative resolution of defects and lead or co-lead internal process improvement initiatives.
• Provide feedback on processes by offering suggestions in line with FINRA’s values of collaboration, expertise, innovation, and responsibility.

• Work on complex features requiring strong knowledge of generative AI industry practices.
• Partner within and across teams to meet shared goals and priorities.
• Openly share progress and priorities with key stakeholders, communicating complex or technical information at the right level.
• Contribute proactively to the full product development lifecycle, from ideation through deployment.

• Develop and refine the system’s integration with large language models (LLMs) and generative AI technologies (agents and MCP servers) as they evolve.
• Design secure patterns for handling sensitive data within AI-powered workflows, ensuring compliance with regulatory requirements.
• Identify innovative applications of AI/LLM capabilities to improve system functionality and user experience.
• Stay informed of advances in LLM frameworks (Lang Graph, Google ADK, AWS Strands), optimization approaches, and emerging AI capabilities.

• Ensure all work products meet or exceed FINRA and team standards for secure development practices.
• Assist with adherence to technology policies and compliance with all security controls.
• Lead secure coding practices and threat modeling for API and infrastructure components.
• Ensure secure handling of personally identifiable information (PII) and sensitive regulatory data throughout the development lifecycle.

• Bachelor’s degree in Computer Science, Information Systems, or related discipline with at least 7…