Engineer in Residence: AA Firewall

Job Description

Job Description

Every large company runs on internal systems that are mission-critical but brittle custom admin panels, ETL pipelines, dashboards, and operational scripts held together by institutional knowledge and hope. This role is to build AI agents that operate behind the enterprise firewall, automating the operational tasks that currently require manual intervention or one-off scripts by securely connecting to internal databases, APIs, and legacy systems.

What you'll build

An agent framework that can securely connect to internal databases, REST/GraphQL APIs, and legacy system interfaces behind corporate firewalls.

A task orchestration layer that lets non-technical operators define multi-step workflows across internal systems using natural language.

An authentication and access control layer that integrates with enterprise identity providers (SSO, LDAP, RBAC) to enforce existing permission boundaries.

A monitoring and audit system that logs every agent action for compliance and debugging.

What you'll do

Design the core agent architecture for operating in constrained network environments where cloud-first assumptions break down.

Build connectors for common enterprise data sources: SQL databases, internal APIs, file shares, legacy mainframe interfaces.

Develop a natural language task definition layer that translates operator intent into safe, auditable multi-step agent actions.

Implement security primitives: credential vaulting, least-privilege execution, action sandboxing, and rollback capabilities.

Work with enterprise design partners to validate the agent framework against real internal tooling pain points.

What you need

Strong backend engineering skills. You have built and shipped production systems that handle real data at real scale.

Deep experience with enterprise infrastructure: databases, APIs, authentication systems, networking constraints.

Hands-on experience building with LLMs, particularly agentic architectures, tool use, and function calling.

Understanding of security and compliance requirements in enterprise environments.

Ability to work autonomously and make product and architecture decisions without waiting for direction.

Helpful but not required

Experience with MCP (Model Context Protocol) or similar tool-use frameworks for AI agents.

Experience building internal developer platforms or internal tooling at scale.

Background in systems integration, middleware, or ETL pipeline development.

Founder or founding engineer experience building infrastructure products.

Who this is for

A builder who sees enterprise internal tooling as an underserved, high-impact problem space.

Someone who understands that the hardest part is not the AI but the integration: auth, permissions, legacy protocols, fragile dependencies.

What to know upfront

This is a 12-week, full-time, on-site residency in Mountain View, California.

Not every residency becomes a company. The goal is to pressure-test the idea quickly and honestly with real users and customers.

You will be building an AI Fund idea, not bringing your own startup idea into the program.

The process typically includes a Builder Event or equivalent working conversation, then a 48-hour Builder Challenge, then panel review with AI Fund build leadership.

The compensation is intentionally modest during the residency because the upside, if the idea works, is a founder-level role.

Compensation

$10,000/month for 12 weeks ($30,000 total). This is a contract role during the residency. If the build leads to a funded company, the next step is a founder-level role with meaningful equity upside.

This is a strong opportunity for a builder who wants to take an idea from concept to working product alongside Andrew Ng and the AI Fund team. We are only considering candidates within commuting distance from Mountain View.

We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.