Principal Engineer - Agentic Engineering

Application Deadline Role Summary

• Act as technical authority across squads, driving consistent engineering practices, architecture alignment, and engineering standards for agentic AI and ML-enabled services.
• Own the technical delivery of CSP''s agent interoperability capability, including shared APIs, Model Context Protocol (MCP) servers, reusable agents, and agent-to-agent interaction patterns.
• Own technical direction and solve complex cross-team challenges across CSP platforms.
• Partner with Engineering Managers, Architects, and Product to shape scalable solutions and influence roadmaps.
• Ensure alignment with enterprise standards, security controls, and regulatory requirements.
• Champion engineering excellence by mentoring senior engineers, promoting reusability and automation, and supporting responsible AI adoption.

Key Responsibilities Technical outcomes

• Drive technical alignment and architecture consistency across squads.
• Deliver reusable APIs, MCP servers, and controls for secure agent-to-agent and tool interaction across CSP.
• Ensure cross-team technical risks are identified, tracked, and mitigated.
• Support resolution of major production issues and escalations for AI and ML services.

Technical contribution

• Define technical direction and enforce engineering standards for agentic AI and MLOps.
• Lead complex design decisions and cross-team integrations across data, model, and platform layers.
• Design, build, and operate production-grade APIs, MCP servers, agent services, and tool integrations used across CSP.
• Define reusable agent interaction and orchestration patterns, covering contracts, versioning, resilience, tracing, security, and auditability.
• Build and improve CI/CD pipelines for ML and agentic workflows, including versioning and rollback controls.
• Promote reusability, scalability, and modernisation across solutions.
• Contribute to enterprise standards and engineering communities, including Inner Source practices.
• Mentor senior engineers and build technical capability across teams.
• Define and enforce non-functional requirements across squads, including reliability, resilience, security, and observability.
• Ensure future readiness through technology evaluation and modernisation planning.

Stakeholder management

• Partner with Product, Architecture, and business stakeholders.
• Influence roadmap and investment decisions using technical evidence and risk-aware options.

AI adoption

• Promote adoption of AI-assisted engineering and agentic delivery patterns at scale.
• Define guardrails, evaluation, and release controls for secure, reliable, and responsible AI usage.

Cost discipline

• Drive cost-efficient architecture and infrastructure decisions across squads.
• Evaluate build versus buy trade-offs for cross-team solutions.
• Ensure licensing, model serving, and cloud costs are optimized across the domain.

Success indicators

• Consistent engineering practices and adopted, reliable shared APIs, MCP servers, and agent interaction patterns across CSP.
• Reduced technical debt and improved platform scalability.
• Effective resolution of cross-team technical challenges.
• Strong technical capability across engineering teams.
• Strong adherence to non-functional requirements across teams.

About you Core skills

• Proven experience as a senior engineer operating across multiple squads or a domain.
• Strong MLOps engineering capability: CI/CD for ML, model lifecycle, and production operations.
• Strong hands-on Python and service engineering, including secure APIs, distributed services, authentication, authorisation, and observability.
• Experience building MCP servers and clients, or equivalent AI tool-integration protocols, and designing resilient agent-to-agent workflows.
• Hands-on experience with container and cloud platforms, including Docker, Kubernetes, and AWS.
• Strong architecture and non-functional thinking across reliability, security, scalability, and performance.
• Ability to influence technical direction and collaborate effectively with Product, Architecture, and Engineering leadership.
• Demonstrated mentoring of senior engineers and contribution to engineering standards.

Bonus skills

• Experience in regulated financial services environments.
• Experience with agentic AI evaluation frameworks, agent interoperability standards, and safety or guardrail design.
• Exposure to model registry, feature store, and data quality frameworks.
• Experience with policy-as-code, platform security automation, and FinOps practices.
• Contribution to Inner Source or enterprise engineering communities.