Overview
In this Production Engineer role, you’ll design, build, and run AI-enabled, production-grade software at scale within Citi’s technology estate. You’ll define agentic workflows and contribute to AI engineering practices across Citi’s India hub during a multi-year transformation. You write reliable code daily, implement observability and automation, and collaborate with cross-functional teams to embed AI into the production lifecycle. This is a hands-on, engineering-led opportunity to shape autonomous systems in a regulated financial environment.
Pay / Benefits
- 27 days annual leave (plus bank holidays)
- Discretionary annual bonus
- Private Medical Care & Life Insurance
- Employee Assistance Program
- Pension Plan
- Paid Parental Leave
Responsibilities
- Design, develop, and maintain production-grade software with reliability and operational excellence
- Architect and implement agentic AI workflows for autonomous production environments
- Integrate LLMs into tooling and incident response via advanced prompt engineering
- Develop AI-native observability for anomaly detection and automated remediation
- Write clean, tested code and promote best practices (code review, pair programming, TDD)
- Drive Continuous Delivery, automation, RCAs, and knowledge sharing
- Manage CI/CD pipelines, IaC tooling, and GitOps for scalable delivery
- Collaborate with platform, data, and product teams to embed AI across deployment lifecycle
- Implement Agile (SCRUM or Kanban) and align with organizational processes
- Operate in a regulated environment with strong compliance awareness
- Coach peers on AI engineering practices and agentic system design
- Communicate progress to stakeholders and foster transparent, innovative culture
Key requirements
- Proven experience in a critical software or production engineering role with high business impact
- Strong programming foundation (Java, Python, Go, or equivalent)
- Hands-on AI/ML engineering with LLM APIs and embeddings
- Expertise in prompt engineering for production use cases
- Experience designing/ deploying agentic systems using LangChain, LangGraph, AutoGen, CrewAI, or equivalents
- Solid understanding of SDLC, GitOps, and modern DevSecOps
- Knowledge of computer science concepts (networks, OS, virtualization, containers)
- Polyglot full-stack mindset and ability to learn new languages
- Experience deploying services at scale on Docker/Kubernetes and service mesh (Istio)
- Experience with CI/CD and IaC tools (Terraform, CloudFormation, Pulumi)
- Experience delivering software with Agile (SCRUM/Kanban)
- Desirable middleware knowledge (MQ, Apache Kafka) and end-to-end observability stacks (Datadog, AppDynamics, Dynatrace)
- Degree in CS/Math/Physics or related subject desirable
- Experience in senior stakeholder management
- Strong written and verbal communication in a global context
- Ability to operate in on-/near-/off-shore matrix reporting structures
- Excellent communication
- Mentorship and coaching
- Collaborative spirit
- AI/ML engineering
- LLM APIs (OpenAI, Anthropic, Gemini)
- Prompt engineering
…
