Lead Software Engineer, Agentic AI

What you'll do

• Design and develop creative software solutions and troubleshoot complex technical problems beyond routine approaches.
• Define and drive the platform roadmap for agent-based capabilities focusing on reliability and usability.
• Lead end-to-end delivery of core agent platform components, including SDKs and integration patterns.
• Establish quality, performance, and operational standards for monitoring, testing, and incident readiness.
• Translate experimentation into production by driving architecture decisions and scalable deployment practices.
• Embed governance, privacy, and model risk considerations into the design of AI platforms.
• Drive team adoption of enterprise-authorized AI-assisted engineering practices to improve code quality and delivery speed.
• Communicate technical strategy and progress to senior stakeholders using data and pragmatic recommendations.

What we're looking for

• Formal training or certification on software engineering concepts and 5+ years of applied experience.
• Proficiency in Python for agent orchestration and LLM tooling, and/or TypeScript, Java, or Go for backend integration.
• Experience designing hybrid search pipelines with vector databases like Pinecone, Milvus, Qdrant, or pgvector.
• Experience building scalable microservices using FastAPI, Spring Boot, or Node.js to expose agent interfaces via REST, WebSockets, or SSE.
• Demonstrated experience leading the use of approved AI-assisted software development tools and coaching engineers on safe adoption.
• Production experience with multi-agent and workflow orchestration frameworks such as LangGraph, AutoGen, CrewAI, LlamaIndex, or Semantic Kernel.
• Deep expertise in tool calling, JSON schema validation, dynamic API integration, sandboxed execution, and Model Context Protocol.
• Advanced knowledge of prompt engineering, chain-of-thought, ReAct, reflection loops, and output guardrails.
• Experience building agent-based systems, orchestration patterns, or evaluation frameworks (preferred).
• Experience designing scalable inference or model serving architectures for latency and cost optimization (preferred).
• Familiarity with responsible AI practices, model risk concepts, and governance-by-design approaches (preferred).
• Experience contributing to open-source software in machine learning or infrastructure ecosystems (preferred).
• Domain knowledge applying machine learning to regulated financial services use cases (preferred).