Forward-Deployed AI Engineer — Agent Workflows & CI/CD

Citigroup Inc.; Greater London; Hybrid; GBP 90,000 - 120,000; Full time

Benefits offered by this job

27 days annual leave

Discretionary annual bonus

Private Medical Care & Life Insurance

Employee Assistance Program

Pension Plan

Paid Parental Leave

Employee discounts

Job summary

Citi London is hiring an intermediate Forward Deployed Engineer to build automated evaluation test suites for AI agents and drive reliable deployment pipelines. You will work with Agentflow Studio, Lightspeed CI/CD, and Python to optimize prompts, test outputs, and security controls in production systems.

The role emphasizes hands-on engineering, collaboration, and delivering measurable business value with robust testing and governance across LOBs.

Qualifications

• Experience in Python and Generative AI application development.
• Proficiency with REST/gRPC APIs, Docker containers and Git workflows.
• Knowledge of AI evaluation frameworks and automated testing.
• Experience building automated test pipelines in CI/CD environments.

Responsibilities

• Construct automated evaluation test suites and measure agent metrics.
• Curate golden datasets and regression testbeds with domain experts.
• Optimize prompts, instructions, and JSON outputs for determinism.
• Authors automated test pipelines and enforces CI/CD gates.
• Analyze agent errors, improve performance, and suggest solutions.
• Implement security and governance policies for safe AI use.
• Monitor evaluation cycles and report to stakeholders.
• Operate with limited supervision as an evaluation SME.

Skills

Python

REST/gRPC APIs

Docker

Git workflows

AI evaluation frameworks

CI/CD

communication

Education

Bachelor's degree in Computer Science or related

Tools

Agentflow Studio

Lightspeed CI/CD

Docker

REST/gRPC

Job description

Citi London is hiring an intermediate Forward Deployed Engineer to build automated evaluation test suites for AI agents and drive reliable deployment pipelines. You will work with Agentflow Studio, Lightspeed CI/CD, and Python to optimize prompts, test outputs, and security controls in production systems.

The role emphasizes hands-on engineering, collaboration, and delivering measurable business value with robust testing and governance across LOBs.