AI Engineer

About the role

As an AI Engineer, you’ll work closely with the founders and our R&D team on XFA’s next security layer: securing AI agents on the devices companies don’t control. AI agents now read files, call tools, and act on company data from personal laptops, contractor machines, and other unmanaged devices. You’ll help give every agent a verifiable identity tied to a human sponsor, grant it only the authority its task needs, and detect when it is manipulated or goes off script. All of that without invading the user’s privacy.

This role suits an experienced engineer who works where AI and security engineering meet. You understand how large language models and agents work under the hood, and you’re just as comfortable reasoning about threat models, key management, and hardware-backed security such as secure enclaves and TPMs. You’ll work across on-device services, our cloud platform, and our AI tooling, including our MCP server.

You’ll help decide how AI agents are secured in practice, from research to production.

Responsibilities

• Design and build identity and authentication for AI agents, with short-lived credentials tied to a human sponsor and bound to the agent’s process with hardware-backed keys (Secure Enclave, TPM 2.0).
• Develop policy-based authorization and delegation for agents, so authority narrows at every step when one agent hands work to another and never exceeds what the task needs.
• Build on-device enforcement where agents actually act, starting with MCP tool calls, with fast local decisions that don’t get in the user’s way.
• Detect threats to and from AI agents: unknown agents, behavior that drifts from an agent’s expected scope, and prompt injection or tampering in inputs, system prompts, memory, and retrieved data, including multimodal content.
• Design privacy-preserving AI pipelines. Process on the device first, filter personal data before it leaves the device, and use confidential computing with remote attestation (e.g. AMD SEV-SNP, Intel TDX, AWS Nitro Enclaves) where server-side processing can’t be avoided.
• Use LLMs where they actually help, such as risk assessment and clear security guidance tailored to the user. Choose between prompting, retrieval-augmented generation, fine-tuning, and small local models based on accuracy, latency, and cost.
• Build evaluation pipelines, attack simulations, and automated tests that measure detection quality and keep AI output reliable in production.
• Follow new work on AI agents, attacks, and standards, and turn what you learn into product.

Requirements

• Several years of experience shipping production software in Golang, Python, TypeScript, or a systems language such as Rust or C++.
• A solid understanding of how LLMs and AI agents work: tokens and context windows, embeddings, tool calling, agent orchestration, and the strengths and limits of different models.
• Hands-on experience building with LLMs (e.g. Claude, GPT, Gemini, or open-weight models), agent frameworks, or the Model Context Protocol (MCP).
• A strong security engineering background: threat modeling, secure system design, applied cryptography, and authentication and authorization protocols (e.g. OAuth 2.0, OpenID Connect, JWT).
• Working knowledge of hardware-backed security: secure enclaves, TPMs, platform key stores, confidential computing, and remote attestation.
• A good grasp of attacks on AI, such as prompt injection, data poisoning, and memory or instruction tampering, and how to defend against them.
• A practical habit of measuring. You know how to evaluate AI output, and you don’t trust a result that only worked once.
• Clear communication, both asynchronous and synchronous, and comfortable working independently and taking initiative in a fast-moving start-up.
• Experience with OS internals or endpoint security on macOS or Windows (e.g. Endpoint Security framework, ETW, eBPF) is a strong plus.
• Experience with policy as code (e.g. Cedar, OPA), workload identity (e.g. SPIFFE/SPIRE), or privacy-enhancing technologies is a plus.
• Fluent in English. Other European languages (e.g. French, German, Dutch) are a plus.

What we offer

• A motivated team with big plans.
• Transparency and open communication.
• A fast-growing company, with international markets and industry-leading clients.
• Flexibility both ways. What counts is the result of the work.
• Work with new technology, putting the latest in AI and cryptography to use.
• A part in a fast-growing start-up where you help shape the company’s future, with a team that celebrates wins and helps each other grow.
• An attractive salary package, with company insurance, meal vouchers, commute coverage, and a 13th month under Belgian employment law.

Want to build the security layer for AI agents? Send your application to people@xfa.tech.