Staff Software Engineer, Platform

About the Role

We are representing a confidential AI platform organization seeking a Staff Software Engineer to join their London team. This position sits within a team focused on agentic AI systems, specifically owning context and memory capabilities that power production AI applications across enterprise and government use cases.

This role is for an engineer who can operate across distributed systems and applied ML, taking ownership of hard technical problems from initial design through production deployment and ongoing evaluation. You will architect the core primitives that enable AI agents to retrieve, store, and reason over long-running context, while also designing the evaluation methodology that proves these systems work reliably at scale.

Responsibilities

• Own end-to-end delivery of large, ambiguous problems in context and memory systems, including backend infrastructure, retrieval algorithms, and production evaluation
• Architect core primitives for agent context management, including knowledge base retrieval, vector storage solutions, and memory strategies
• Design and maintain evaluation methodology for memory and retrieval quality, including rubrics and benchmarks that catch regressions before customer impact
• Set technical standards adopted across the engineering team, covering architectural patterns, evaluation practices, and failure handling approaches
• Partner with software and ML engineering peers on a unified roadmap, coordinating across workstreams where memory and context intersect with orchestration, evaluation, and systems optimization
• Debug and resolve critical production issues related to context and memory, including retrieval accuracy, context isolation across tenants, and relevance degradation at scale

What We're Looking For

• 8+ years of engineering experience with a proven track record owning production systems end-to-end, not just implementing scoped work
• Direct experience with ML and information retrieval problems underlying modern AI systems: embeddings, vector search, retrieval augmented generation, fine-tuning, or agent memory architectures
• Strong capability across both software engineering and applied ML—you don't need equal depth in both, but sufficient range to make sound technical decisions independently
• Proficiency in Python and experience with production ML infrastructure including containers, cloud platforms, and CI/CD
• Track record of establishing technical standards that outlasted individual projects and influencing decisions beyond your immediate team through design reviews, technical writing, or mentorship
• Experience scaling products at hyper-growth startups (preferred)
• Experience with agent orchestration frameworks and multi-agent systems in production (preferred)
• Contributions to open-source agentic AI projects (preferred)

How We Work With You

Candidates apply directly through Get A Job.ai. Our talent team will conduct an initial screening to understand your background and confirm alignment with the role requirements. Qualified candidates are then submitted to our client for their review and interview process. Please do not attempt to contact the client directly, as all communication is managed through Get A Job.ai to ensure a professional and organized hiring process.

Pay

Compensation details will be discussed with qualified candidates during the screening process.

Equal Employment Opportunity: Get A Job.ai is committed to inclusive hiring practices and equal opportunity employment. We evaluate all candidates based on qualifications and experience regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability status, gender identity, or veteran status.