Production AI engineer

Citi; Greater London; Hybrid; GBP 100,000 - 170,000; Full time

Benefits offered by this job

Hybrid workplace

Private medical care

Life insurance

Pension plan

Parental leave

Learning resources

Job summary

Citi ищет Production Engineer, ответственного за проектирование, разработку и эксплуатацию интеллектуальных систем в глобальной production-среде. Работа предполагает фокус на инженерное мастерство, AI‑native разработку и крупномасштабные распределенные системы.

Роль включает внедрение агентных рабочих процессов, интеграцию LLM, обеспечение надежности и операционной эффективности, а также развитие observability и автоматизацию в рамках регуляторной финансовой среды.

Qualifications

• Опыт в критических программных системах с высокой бизнес-значимостью и сильной основой в Java, Python или Go.
• Опыт работы с AI/ML инженерией — включая LLM API, embedding-модели и вектора
• Навыки проектирования и эксплуатации агентских систем и мульти-агентной оркестрации
• Понимание SDLC, GitOps и DevSecOps, владение современными практиками разработки
• Умение работать в глобальной среде и эффективно коммуницировать с заинтересованными лицами

Responsibilities

• Проектирование, разработка и поддержка production-grade систем с упором на надежность и масштабируемость.
• Разработка и внедрение агентных AI-рабочих процессов для автономного принятия решений.
• Интеграция LLM в операционные инструменты и пайплайны реагирования на инциденты.
• Развитие observability и автоматизации для предотвращения падений производительности.
• Поддержка CI/CD, IaC и GitOps для безопасной доставки кода в крупных окружениях

Skills

Java

Python

Go

AI/ML engineering

Prompt engineering

Distributed systems

DevSecOps

GitOps

Education

Bachelor's degree in Computer Science

MSc/PhD desirable

Tools

LLM APIs

LangChain

Kubernetes

CI/CD tooling

Infrastructure as Code

Job description

Описание

The Production Engineer is a pivotal role within Citi's Technology organisation, responsible for designing, building, and operating the intelligent systems that underpin our global production environment. This is an engineering-first position at the intersection of software craftsmanship, AI-native development, and large-scale distributed systems.

Задачи

Designs, develops, and maintains production-grade software systems with a strong emphasis on reliability, scalability, and operational excellence across Citi's global technology estate. Architects and implements agentic AI workflows — building autonomous systems that can reason, plan, and act across production environments with minimal human intervention. Applies advanced prompt engineering techniques to integrate large language models (LLMs) into operational tooling, incident response pipelines, and developer productivity platforms. Leads the development of AI-native observability solutions — leveraging intelligent agents to detect anomalies, predict failures, and automate remediation before issues impact end users. Writes clean, well-tested, and well-documented code across the full stack; champions engineering best practices including code review, pair programming, and test-driven development. Drives Continuous Delivery and Automation efforts across supported applications by means of Root Cause Analysis reviews, knowledge management, performance tuning, and user training. Operates and evolves CI/CD pipelines, Infrastructure-as-Code tooling, and GitOps workflows to support rapid, safe delivery of software at scale. Collaborates with platform, data, and product engineering teams to embed AI capabilities into the production lifecycle — from deployment to decommission. Implements the Agile Framework through one of its implementations (SCRUM or Kanban) and ensures it integrates with overall organisation processes. Operates within a highly regulated financial environment, maintaining in-depth understanding of compliance requirements and their implications for system design and data handling. Coaches and mentors team members on AI engineering practices, prompt design patterns, and agentic system architecture — fostering a culture of continuous learning and technical excellence. Avidly communicates progress and project status across the organisation and ensures that stakeholders are managed appropriately throughout the execution period. Fosters a culture that promotes transparency and innovation for increased team productivity.

Требования

Demonstrable experience in a critical software engineering or production engineering role with high business impact and a strong programming foundation (Java, Python, Go, or equivalent). Hands-on experience with AI/ML engineering — including working with LLM APIs (OpenAI, Anthropic, Gemini, or open-source equivalents), embedding models, and vector databases. Proven expertise in prompt engineering: designing, iterating, and evaluating prompts for production use cases including classification, summarisation, code generation, and autonomous decision-making. Experience designing and deploying agentic systems using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or equivalent — including multi-agent orchestration and tool-use patterns. Excellent engineering skills and strong understanding of Software Development Lifecycle, GitOps, and modern DevSecOps practices. Excellent working knowledge of key computer science concepts (networking, operating systems, virtualisation, containerisation, etc.). Polyglot full-stack developer mentality and ability to pick up new languages and skills. Excellent debugging and analytical skills: ability to isolate root cause across networking/infrastructure, application, and database stacks. Experience of delivering software using Agile delivery methodologies is a must (SCRUM/Kanban). Experience of senior stakeholder management. Consistently demonstrates clear and concise written and verbal communication skills. Ability to operate in a global environment with on-/near-/off-shore matrix reporting structures. Learnability — Rapidly acquires new skills, frameworks, and paradigms. In a field evolving as fast as AI engineering, the ability to learn is the most durable skill of all. Teachability — Receives feedback with openness and intellectual humility. Actively seeks mentorship and applies guidance to accelerate growth. Flexibility & Adaptability — Thrives in ambiguity. Pivots gracefully when requirements shift, technology evolves, or priorities change — without losing momentum or quality. Engineering Mindset — Approaches every problem systematically: decomposing complexity, forming hypotheses, and validating solutions with rigour and precision. Product-Minded Thinking — Understands that code serves users and business outcomes. Balances technical elegance with pragmatic delivery and user impact. Collaborative Spirit — Builds trust across disciplines — engineering, product, operations, and leadership. Elevates the team's collective output through generosity and clear communication. Intellectual Curiosity — Asks "why" before "how". Explores the edges of what's possible with AI and production systems, driven by genuine fascination rather than obligation. Ownership & Accountability — Takes end-to-end responsibility for what they build. Does not hand off problems — follows through from design to deployment to post-incident review.

Будет плюсом

• Operational experience of deploying and running services at scale on top of Docker/Kubernetes stack and a service mesh (Istio or equivalent) is highly desirable
• Operational experience with orchestration tools for CI/CD and Infrastructure-as-Code tooling (Terraform, CloudFormation, Pulumi, etc.) is highly desirable
• Operational experience of using middleware technologies (MQ, Apache Kafka, etc.) to run services at scale is desirable
• Strong experience with end-to-end observability stacks (Datadog, AppDynamics, Dynatrace, etc.) is desirable
• Degree in Computer Science, Mathematics, Physics, or a related technical subject is desirable

Условия

• business casual workplace with a hybrid working model (up to 2 days working at home per week)
• competitive base salary (which is annually reviewed)
• 27 days annual leave (plus bank holidays)
• A discretional annual performance related bonus
• Private Medical Care & Life Insurance
• Employee Assistance Program
• Pension Plan
• Paid Parental Leave
• Special discounts for employees, family, and friends
• Access to an array of learning and development resources