Senior AI System Engineer

Responsibilities:
Drive Architectural Change: Lead the technical strategy and hands-on execution for building production-grade multi-agent systems and security chatbots.
Scale Our Capabilities: Act as an accelerator for the team, taking ownership of new AI feature development so we can keep pace with rapidly growing product demands.
Build Applied LLM Workflows: Design secure, maintainable workflows using for AI SOC use cases like alert triage, summarisation, and workflow automation.
Own Evaluation (Evals): Create test sets, define success metrics (accuracy, faithfulness, latency), and run regression tests before and after changes for your features.
Monitor Production Behaviour: Debug hallucinations and systematically reduce failure modes through better retrieval, prompting, and guardrails (not just "tweak the temperature").
Establish Engineering Standards: Define robust patterns for context engineering, tool design, retrieval, and harness engineering to ensure our agents are rigorously evaluated for quality and safety.
Champion Security-First AI: Ensure data privacy, access controls, and prompt injection defences are embedded deeply into our multi-agent architectures.
Collaborate Cross-Functionally: Work seamlessly across Data Science, Engineering, Product and Platform teams to guide emerging AI capabilities from prototype to production.
Requirements:
8+ years of professional software engineering experience, with a strong foundation in designing and operating reliable, production-grade systems.
Programming Languages: Expertise in. NET, TypeScript or Python is expected.
1-2 years of hands-on applied AI experience specifically focused on building multi-agent systems, chatbots, tool-using agents, or AI-powered automation.
Cloud-Native AI Expertise: Practical experience using cloud AI services (AWS Bedrock strongly preferred) and LLM provider SDKs (such as Claude AgentSDK).
Core AI Technical Depth: Proven understanding of enterprise RAG systems, Model Context.
Protocol (MCP) tool integrations, context engineering, and harness engineering for evaluations.
Project Leadership: A track record of driving complex technical projects and influencing architectural decisions in a fast-paced, low-bureaucracy environment.
Security Mindset: Strong grasp of AI security frameworks, data privacy, auditability, and safe tool-calling practices for autonomous or semi-autonomous systems.
Experience building security automation, SOAR, SOC, threat intelligence, detection engineering, or incident response products.
Familiarity with AI security frameworks, prompt injection defences, agent sandboxing, policy-based tool control, or AI governance practices.
Experience building evaluation harnesses for AI quality, latency, cost, safety, and reliability.
Experience using AI coding tools such as Cursor, Claude Code, GitHub Copilot, or similar tools in real engineering workflows.

Experience
8-12 yrs