2 months ago
London, United KingdomStaff+
Responsibilities
- Design, develop, maintain, and operate reliable and scalable production-grade software systems.
- Architect and implement agentic AI workflows using LLMs, prompt engineering, multi-agent orchestration, and tool-use patterns.
- Build AI-native observability solutions that detect anomalies, predict failures, and automate remediation.
- Write clean, tested, and documented full-stack code while applying engineering practices such as code review and pair programming.
- Drive continuous delivery, automation, root-cause analysis, knowledge management, performance tuning, and user training.
- Operate CI/CD pipelines, infrastructure-as-code tooling, and GitOps workflows.
- Deploy and run services at scale using containerization, orchestration, middleware, and observability platforms.
- Collaborate with platform, data, and product engineering teams to embed AI throughout the production lifecycle.
- Maintain compliance with requirements affecting system design and data handling in a regulated financial environment.
- Coach and mentor team members on AI engineering, prompt design, and agentic system architecture.
- Communicate project progress, manage stakeholders, and contribute to technical planning and organizational processes.
Requirements
- Demonstrable experience in a critical software or production engineering role with strong programming skills in Java, Python, Go, or equivalent.
- Hands-on AI/ML engineering experience with LLM APIs, embedding models, and vector databases.
- Experience designing, iterating, and evaluating prompts for production use cases such as classification, summarization, code generation, and autonomous decision-making.
- Experience designing and deploying agentic systems with frameworks such as LangChain, LangGraph, AutoGen, or CrewAI, including multi-agent orchestration and tool use.
- Strong understanding of software development lifecycle practices, GitOps, DevSecOps, networking, operating systems, virtualization, and containerization.
- Polyglot full-stack development ability and willingness to learn new languages and skills.
- Strong debugging and analytical skills across networking, infrastructure, application, and database stacks.
- Operational experience with Docker, Kubernetes, and a service mesh such as Istio or equivalent is highly desirable.
- Operational experience with CI/CD orchestration and infrastructure-as-code tools such as Terraform, CloudFormation, or Pulumi is highly desirable.
- Experience using middleware such as MQ or Apache Kafka to run services at scale is desirable.
- Experience with observability platforms such as Datadog, AppDynamics, or Dynatrace is desirable.
- A degree in Computer Science, Mathematics, Physics, or a related technical subject is desirable.
- Experience with senior stakeholder management and clear written and verbal communication.
- Ability to work in a global environment with onshore, nearshore, offshore, and matrix reporting structures.
- Experience delivering software using Scrum or Kanban is required.
Benefits
- Hybrid working model with up to two days working from home per week.
- Competitive base salary reviewed annually.
- 27 days of annual leave plus bank holidays.
- Discretionary annual performance-related bonus.
- Private medical care and life insurance.
- Employee assistance program.
- Pension plan.
- Paid parental leave.
- Employee, family, and friends discounts.
- Access to learning and development resources.
- Full-time position in a business-casual workplace.
Tech Stack
Categories
About Citi
Citi is a public financial-services company offering consumer and institutional banking, credit cards, wealth management, treasury and trade solutions, and capital-markets services. It serves individuals, corporations, financial institutions, and governments in more than 160 countries and jurisdictions, earning interest and fee income from lending, payments, trading, and advisory. Founded in 1812 and headquartered in New York, it trades on the NYSE under the ticker C.