IT Officer, Business Solutions I (Agentic AI Developer)

The Agentic AI Developer will design and implement production-grade agentic AI systems integrating large language models with tools, data sources, and enterprise workflows to support the World Bank Group's AI platform and product development initiatives. The role involves architecting multi-agent AI systems, integrating LLMs, developing tools and APIs, conducting evaluation and testing, deploying applications on cloud infrastructure, and providing documentation and knowledge transfer.

Responsibilities

• Architect and implement multi-agent and single-agent AI systems using frameworks such as LangGraph, LangChain, AutoGen, CrewAI, or equivalent.
• Design agent reasoning loops, tool-calling mechanisms, memory management strategies, and orchestration logic.
• Develop agents capable of interacting with APIs, databases, document repositories, and internal WBG systems.
• Implement retrieval-augmented generation (RAG) pipelines to ground agents in institutional knowledge and internal data.
• Integrate leading LLM providers (Anthropic Claude, OpenAI GPT, Google Gemini) into agent workflows via APIs.
• Design and refine system prompts, few-shot examples, and chain-of-thought instructions to guide agent behavior reliably.
• Implement guardrails, output validation, and fallback logic to ensure safe and accurate agent responses.
• Build custom tools and function-calling interfaces that agents can invoke (e.g., search tools, database queries, document processors, email senders).
• Ensure tool schemas are well-defined, type-safe, and robust against edge cases.
• Integrate with internal WBG platforms and data sources as required.
• Design evaluation frameworks to assess agent performance, accuracy, groundedness, and safety.
• Conduct red-teaming and adversarial testing to identify failure modes and jailbreak risks.
• Establish benchmark datasets and automated testing pipelines for regression monitoring.
• Package and deploy agentic applications on cloud infrastructure (Azure, GCP, or equivalent).
• Implement observability and monitoring for agent behavior, latency, and token usage.
• Maintain CI/CD pipelines for continuous delivery of agent updates.
• Produce technical documentation covering architecture decisions, agent workflows, and API specifications.
• Provide knowledge transfer sessions and code walkthroughs for internal engineering teams.
• Contribute to internal guidelines and best practices for agentic AI development at WBG.

Requirements

• Master's degree in Computer Science, Artificial Intelligence, Software Engineering, or a related field, with a minimum of 5 years of relevant experience; or a Bachelor's degree with a minimum of 7 years of relevant experience.
• Minimum 5–7 years of software development experience, with at least 2 years focused on AI/ML systems.
• Demonstrated hands-on experience building agentic or LLM-powered applications in production environments.
• Proficiency in Python; familiarity with TypeScript/JavaScript is a plus.
• Experience with at least one agentic framework (LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel, or similar).
• Strong understanding of LLM APIs, function/tool calling, RAG architectures, and vector databases (e.g., Pinecone, Weaviate, pgvector).
• Experience with cloud platforms (Azure preferred; GCP or AWS acceptable).
• Familiarity with containerization (Docker, Kubernetes) and CI/CD practices.
• Strong analytical and problem-solving skills with the ability to translate ambiguous business requirements into technical solutions.
• Excellent written and verbal communication skills in English.
• Ability to work independently and collaboratively in a multicultural environment.
• Demonstrated ability to manage multiple workstreams and deliver under deadlines.
• Preferred: Experience with enterprise AI governance, responsible AI frameworks, or AI safety practices.
• Preferred: Prior experience working in international organizations or development finance institutions.
• Preferred: Familiarity with knowledge management systems, document intelligence, or enterprise search.

Skills

• Software Development
• AI/ML Systems
• Agentic AI Development
• Python Programming
• TypeScript
• JavaScript
• Agentic Frameworks
• LangChain
• LangGraph
• AutoGen
• CrewAI
• Semantic Kernel
• LLM APIs
• Function Calling
• Tool Calling
• RAG Architecture Development
• Vector Databases
• Pinecone
• Weaviate
• pgvector
• Cloud Platforms
• Azure
• Google Cloud Platform
• AWS
• Containerization Technologies
• Docker Containers
• Kubernetes
• CI/CD
• Technical Solutions Design
• Enterprise AI Governance
• Responsible AI Frameworks
• AI Safety Practices
• Knowledge Management
• Document Intelligence
• Enterprise Search

Languages

English