Senior Software Engineer – Secure AI Agent Access Platform (Python)

We’re building foundational infrastructure to secure AI agents — including their identities, access patterns, and interactions with sensitive systems and data. This includes designing intelligent, dynamic mechanisms for ephemeral access control, secrets management, and agent/user identity tailored to modern agent frameworks such as LangChain, LangGraph, Semantic Kernel, AutoGen, and beyond.

You’ll help define how agents (both machine and human-facing) authenticate, receive scoped access, perform actions securely, and leave behind a verifiable audit trail.

This is a unique opportunity to be part of a start-up inside the company — building the platform from scratch at one of the most cutting-edge intersections of AI, identity, and security.

Responsibilities:

• Develop secure, scalable Python services to support agent identity, secrets access, credential management, and authorization flows.
• Implement JWT-based agent/user authentication, and real-time policy checks based on agent context and tool usage.
• Build SDKs, wrappers, and tool integrations that enable popular agent frameworks (LangChain, LangGraph, Semantic Kernel, etc.) to securely request and use secrets.
• Collaborate closely with the architect and other engineers to design components with clear boundaries and clean contracts.
• Ensure secrets and credentials are injected only when needed, redacted from logs, and never persist in agent memory or prompts.
• Write thorough tests and maintain high-quality, well-documented code.
• Work cross-functionally with internal platform, AI, and security teams to understand requirements and refine implementation plans.

Qualifications:

• 5+ years of backend or systems development experience, primarily in Python.
• Strong understanding of secure API development, authentication models (JWT, OAuth2), and basic access control patterns.
• Exposure to secrets management platforms (AWS Secrets Manager, CyberArk Conjur, etc.) - bonus.
• Familiarity with or strong interest in AI agent frameworks (LangChain, AutoGen, LlamaIndex, etc.).
• Exposure to identity and access management concepts — especially in zero-trust or dynamic runtime environments — is highly valuable.
• Experience building SDKs or developer-focused tools is a plus.
• A security-first mindset, attention to detail, and strong debugging/testing skills.
• Excellent communication and collaboration skills — you’ll be interfacing with multiple engineering groups to deliver complete and secure solutions.