Staff Applied AI Engineer: Production AI & LLM Systems

Aviva plc; Greater London; Hybrid; GBP 124,000 - 135,000; Full time

Benefits offered by this job

Bonus programme

Generous pension

Private Medical Benefit

Share matching plan

Flexible working

Volunteer days

Discounts on Aviva products

Job summary

Aviva seeks a Staff Applied AI Engineer in London and other UK cities to design and deploy production AI agents across customer and internal domains. You'll own architectures, collaborate with product teams, and implement robust evaluation and memory strategies to ensure safe, scalable AI delivery.

The role emphasizes context pipelines, memory architectures, and enterprise MCP integration, with a focus on responsible AI and regulatory compliance within a high-trust financial services setting.

Qualifications

• Experience building production-grade Python AI/ML code.
• Proven track record with LLM-powered applications and agent pipelines.
• Strong understanding of context pipelines and memory architectures.
• Experience with AWS or cloud infra and orchestration tools.

Responsibilities

• Design and deliver production AI agents and multi-agent pipelines.
• Own architecture and framework choices for AI systems.
• Build evaluation frameworks to measure AI quality, safety and fairness.
• Develop context pipelines with chunking, embedding selection and hybrid search.
• Integrate MCP servers and enterprise tooling.
• Maintain production reliability and incident response for AI agents.
• Mentor junior engineers and participate in architecture reviews.
• Ensure compliance with FCA Consumer Duty and GDPR.

Skills

Python

LLM development

Agent systems

Context engineering

Cloud infrastructure

Production engineering

Stakeholder comms

Memory architectures

Evaluation frameworks

Tools

Claude Code

Cursor

Codex

AWS Strands

OpenAI Agents SDK

MCP

LangSmith

HuggingFace TRL

Job description

Aviva seeks a Staff Applied AI Engineer in London and other UK cities to design and deploy production AI agents across customer and internal domains. You'll own architectures, collaborate with product teams, and implement robust evaluation and memory strategies to ensure safe, scalable AI delivery.

The role emphasizes context pipelines, memory architectures, and enterprise MCP integration, with a focus on responsible AI and regulatory compliance within a high-trust financial services setting.