Senior AI Engineer

Their mission: safeguard the digital world and empower people to work securely and confidently. Join us in our pursuit to defend data and protect people.

How We Work:

• Architect and build production-grade AI-powered applications and agentic systems end-to-end, including front-end, back-end, data pipelines, APIs, and multi-model AI integrations.
• Design and operate agentic AI systems — including multi-agent orchestration, tool/function calling pipelines, memory and context management strategies, and dynamic intent routing — with a strong grasp of how these systems behave and fail in production.
• Own the full lifecycle of complex AI systems: requirements, architecture design, implementation, evaluation harness construction, deployment, observability, and post-launch iteration.
• Drive technical decision-making on model selection, retrieval architectures (RAG, vector search, hybrid), prompt engineering strategies, and LLM API integrations — with clear communication of tradeoffs to engineering and business stakeholders.
• Design for scale and reliability: apply software engineering fundamentals including system design principles, data structures, algorithms, and distributed systems thinking to AI application architecture.
• Build evaluation and observability infrastructure — including automated eval harnesses, LLM-as-judge pipelines, latency/cost monitoring, and regression frameworks — to continuously measure and improve system quality.
• Define and maintain engineering standards for AI development: reusable patterns, integration abstractions, documentation, and testing practices adopted across the team.
• Mentor and technically guide junior engineers; conduct code and design reviews, and actively raise the technical bar of the team.

• 6+ years of hands-on software engineering experience, with at least 3 years building and shipping production AI/ML systems with real users and measurable business impact.
• Deep proficiency in Go, Python and strong familiarity with typed, production-quality codebases; solid command of data structures, algorithms, and system design principles — capable of designing scalable services, handling concurrency, and reasoning about performance and failure modes.
• Hands-on experience building agentic AI systems — including multi-step reasoning pipelines, tool/function calling, dynamic planning, and agent orchestration frameworks (e.g. LangGraph, AutoGen, CrewAI, or custom implementations).
• Working knowledge of the MCP (Model Context Protocol) or comparable tool-calling and context injection protocols — including how context windows are managed, how tools are registered and invoked, and how to architect reliable agent-tool interactions.
• Strong experience with memory and context management in LLM systems: short-term context strategies, long-term memory via vector stores or knowledge graphs, conversation summarisation, and retrieval-augmented generation (RAG) architectures.
• Experience designing and building evaluation harnesses for AI systems: automated test suites, LLM-as-judge patterns, benchmark construction, and production monitoring for quality, latency, and cost.
• Production experience with LLM APIs (OpenAI, Anthropic, or equivalent), including prompt engineering, structured output, fine-tuning tradeoffs, and multi-model orchestration.