Advisory Engineer
Description & Overview
Job Title: Advisory Engineer Agentic AI
Location: London, UK
Role: Hybrid (3 days to office and 2 days remote)
Position: Full-time (Permanent Role)
We are building a next-generation AI innovation hub focused on developing advanced agent systems that operate seamlessly across mobile, edge, and cloud environments. Our mission is to design scalable, production-ready AI platforms that bring cutting-edge foundation models and agentic orchestration into real-world applications at global scale.
You will join a high-caliber team of engineers and researchers shaping large-scale AI systems that serve millions of users across diverse device ecosystems. This is a rare opportunity to define foundational agent infrastructure in a rapidly evolving AI landscape.
Responsibilities
Architect Agent Systems
- Design and own the architecture of production-grade agent systems.
- Define patterns, abstractions, and SDK frameworks (e.g., LangGraph/Pydantic-based graph systems or similar) that serve as the foundation for broader engineering teams.
- Ensure scalability, extensibility, and long-term maintainability.
Lead Orchestration & Routing Strategy
- Define the technical vision for orchestration services, model routing (edge-to-cloud), and multi-agent coordination.
- Make architectural decisions balancing latency, cost, capability, and reliability.
- Design robust fallback and routing mechanisms for heterogeneous model environments.
Drive Cross-Team Integration
- Collaborate with product and platform teams to translate business requirements into technical specifications.
- Coordinate with infrastructure and data teams to manage system dependencies.
- Enable integration across distributed teams and services.
Establish Reliability & Safety Standards
- Define guardrail policies, fallback chains, and safety constraints for agent systems.
- Own incident response processes and post-mortem frameworks.
- Drive production-readiness standards and operational excellence.
Build Observability Infrastructure
- Architect tracing, logging, and monitoring systems for agent behavior at scale.
- Develop dashboards, metrics, and alerting pipelines.
- Enable continuous performance evaluation and optimization.
Mentor and Grow the Team
- Lead architectural decision-making within the squad.
- Conduct code reviews and establish engineering best practices.
- Mentor engineers and elevate system design standards.
Shape the Technical Roadmap
- Contribute to planning cycles and long-term architectural strategy.
- Identify technical risks and drive reliability and velocity improvements.
- Influence technical direction beyond the immediate team.
Core Skills
- Expert-level Python (async programming, performance optimization, SDK/library design).
- Deep understanding of agentic frameworks (LangChain, LangGraph, LlamaIndex, AutoGen or similar), including internal mechanics.
- Proven experience shipping production-grade agent systems serving real users at scale.
- Strong distributed systems design: state management, message queues, service meshes, reliability patterns.
- Experience with model routing strategies, embedding similarity search, and edge-cloud orchestration.
- Ability to independently make architectural decisions and clearly articulate trade-offs.
Bonus Skills
- Experience with agent communication protocols (e.g., MCP or equivalent).
- Background in edge/on-device deployment with memory and latency constraints.
- Contributions to open-source agent frameworks.
- Experience operating ML platforms or MLOps infrastructure.
- Experience with systems languages (Go, Rust) for performance-sensitive components.
- Public technical contributions (talks, publications, blog posts) in AI/agent systems.
Qualifications
- 8+ years of software engineering experience (6+ with MS degree).
- 2+ years focused on ML/AI systems or LLM-driven applications.
- Demonstrated technical leadership and ownership of systems end-to-end.
- Experience handling production incidents and operational processes.
- Proven ability to influence technical direction across teams.
What We Offer
- Career advancement opportunities within a fast-growing AI initiative.
- Access to advanced technical training programs.
- Performance-based reward structures.
- Flexible hybrid work model (3:2).
- Comprehensive benefits package including life insurance and mobility incentives.