2 days ago
London, United KingdomStaff+
Responsibilities
- Build and integrate generative AI applications using managed GenAI APIs and open-model endpoints.
- Design context-engineering workflows involving instructions, retrieved knowledge, tools, memory, and task metadata.
- Develop prompt-engineering workflows and AI-powered business processes.
- Build and maintain RAG systems with chunking, embeddings, hybrid search, and re-ranking.
- Assist with knowledge graphs and Graph RAG pipelines for multi-hop reasoning and traceable responses.
- Build agentic workflows with tool-calling, structured planning, memory, and agent frameworks.
- Integrate agents with external tools and data through MCP and support A2A-based collaboration.
- Deploy, monitor, and maintain GenAI and agentic applications in production.
- Perform data preprocessing, document ingestion, and API development.
- Participate in collaboration, code reviews, testing, documentation, and responsible AI practices.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Data Science, AI, or a related field.
- Commercial experience in software or AI development with exposure to generative AI and agentic AI.
- Experience delivering AI or GenAI projects in a collaborative environment.
- Proficiency in Python for GenAI development, preprocessing, and scripting.
- Understanding of foundation models, LLMs, tokenization, embeddings, and context windows.
- Hands-on experience with prompt engineering, context engineering, and RAG systems.
- Familiarity with vector databases, hybrid search, knowledge graphs, Graph RAG, and multi-hop retrieval.
- Exposure to tool-using agents and multi-step workflows using frameworks such as Google ADK, LangGraph, CrewAI, or OpenAI Agents SDK.
- Working knowledge of tool or function calling, MCP, A2A, session and state management, memory, guardrails, and execution controls.
- Practical experience consuming GenAI APIs such as OpenAI, Gemini, or Claude, and using LangChain or LlamaIndex.
- Understanding of application deployment, Docker, and Git.
- Awareness of AI compliance, data privacy, guardrails, and responsible AI principles.
- Exposure to AWS, GCP, or Azure is preferred.
- Strong teamwork, communication, analytical, learning, and attention-to-detail skills.
Benefits
- Hybrid working model with up to two days working from home per week.
- 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.
- Special discounts for employees, family, and friends.
- Access to learning and development resources.
- Full-time employment in a business-casual workplace.
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.
