AI Engineer - ED5

Key Responsibilities

• AI System Architecture & Engineering
• Design, build, and operate production AI-enabled systems solving complex product and business challenges.
• Architect agentic systems with autonomous tool use, multi-step reasoning, and controlled execution.
• Define and enforce Model Context Protocol (MCP) patterns for tools, memory, policies, and system boundaries.
• Make informed model selection decisions, balancing quality, latency, cost, and reliability.
• Treat prompts, context, and agent flows as versioned, testable, and observable system components.

• Lead high-impact AI initiatives from architecture through delivery and long-term ownership.
• Decompose ambiguous problems into clear technical strategies.
• Identify failure modes, risks, and trade-offs early and design safeguards.
• Influence cross-team direction through technical judgment and example.
• AI Engineering Standards
• Define patterns for:
  • Agent behaviour and autonomy
  • Prompt and context design
  • Evaluation and regression detection
  • Safe, explainable AI in production
• Embed AI-assisted development practices across teams (code generation, testing, debugging, documentation).
• Ensure AI becomes a default engineering capability—not an experiment.
• Quality, Reliability & Governance
• Implement monitoring, evaluation, and safeguards for production AI systems, including:
• Hallucination and error detection
• Behavioural regression and drift
• Traceability and explainability
• Own system performance, cost efficiency, security, and compliance.
• Maintain long-term operational health beyond initial delivery.
• Mentorship & Collaboration
• Mentor engineers through design reviews, pairing, and architectural guidance.
• Raise AI fluency and system thinking across teams.
• Partner with Product and Design to translate intent into scalable, maintainable AI solutions.
• Clearly communicate AI trade-offs to technical and non-technical stakeholders.

Qualifications

• Required
  • Python, C#, MongoDB, SQL Server, OpenSearch.
  • Extensive experience building and operating complex production systems.
  • Deep hands-on experience with agentic AI systems in production (autonomous tools, multi-step workflows).
  • Strong expertise in Model Context Protocols (MCPs) or equivalent frameworks.
  • Strong understanding of:
    • Model capabilities and trade-offs (latency, cost, reasoning quality)
    • Context window strategies
    • Prompt design and system boundaries
    • Experience with both frontier and open-source models.
  • Proven ability to scale AI systems (latency optimisation, caching, parallelisation, cost control).
  • Demonstrated track record of moving AI systems from prototype to sustained production.
  • Strong judgment and ability to operate in ambiguous environments.
• Preferred
  • Experience in defining engineering standards adopted across teams.
  • Experience shaping AI platforms or shared agentic frameworks.
  • Background in cloud-native, SaaS, or enterprise environments.
  • Experience in regulated or mission-critical systems.

What We Value