Short Term Consultant - Software Engineer (Applied AI)

Please submit your CV and cover letter to embed@worldbank.org by May 15, 2026.

About the World Bank and eMBe

DThe World Bank is a global development institution committed to reducing poverty and promoting shared prosperity. Through its Development Economics Vice Presidency (DEC), the Bank generates cutting-edge research and data to inform policy design and implementation worldwide

.Within DEC, the Mind, Behavior, and Development Unit (eMBeD) applies insights from behavioral science to improve development outcomes. The unit works across sectors—including education, labor markets, public health, and digital services—to design, test, and scale interventions that improve decision-making and service delivery. Increasingly, eMBeD integrates artificial intelligence (AI) into its operational and research portfolio to accelerate learning, enhance service delivery, and support governments in adopting evidence-based and human-centered innovations

.
Role Purpo

seThe Software Engineer (Applied AI) is responsible for the production engineering of eMBeD’s AI-enabled platforms and for establishing the engineering substrate that enables non-engineering team members to contribute safely and effectively at scal

e.The role combines hands-on systems engineering, AI application development, and institutional capacity building, ensuring that AI solutions are robust, secure, and aligned with responsible AI standards within a development contex

t.Duties and Accountabiliti

esThe Software Engineer (Applied AI) wil

• l:Perform advanced-level engineering work on AI-enabled applications with limited supervision, including system architecture design, production deployment, and operational ownershi
• p.Propose and implement solutions to moderately complex technical challenges in applied AI engineering, including agentic memory design, Model Context Protocol (MCP) server architecture, and evaluation infrastructur
• e.Translate engineering trade-offs into clear, outcome-oriented language for non-technical stakeholders, including unit leadership and behavioral science team
• s.Provide technical guidance, code review, and architectural input to behavioral scientists and economists working in AI-assisted development environment
• s.Serve as a technical resource for security, reliability, and responsible AI considerations across the unit’s portfoli

o.
Key Responsibilit

ies1. Production Engineering for AI Applicati

• onsDesign, implement, and maintain MCP server infrastructure and reusable agentic patterns supporting eMBeD’s AI-enabled applicatio
• ns.Manage cloud infrastructure, container orchestration, CI/CD pipelines, and deployment environments across development, staging, and producti
• on.Ensure scalability, reliability, and performance of deployed AI applicatio

ns.2. Engineering Standards and Quality Assura

• nceEstablish and enforce engineering standards for AI-assisted development, includi
• ng:Code review protoc
• olsAutomated testing framewo
• rksEvaluation harnes
• sesSecurity checkli
• stsReview code and architectural outputs generated using agentic coding tools, maintaining quality without limiting team agili
• ty.Develop and maintain evaluation systems, includi
• ng:Golden datas
• etsLLM-as-judge pipelines with bias controls (verbosity, position, sycophan
• cy)Human-in-the-loop review workfl
• owsDocument architecture, standards, and operational procedures as living knowledge asse

ts.3. Security, Privacy, and Responsible

• AIImplement security controls across the AI application lifecycle, including authentication, role-based access control, secrets management, and encrypti
• on.Design and test safeguards against AI-specific threats such as prompt injection, data exfiltration, and model misu
• se.Implement guardrails, output validation mechanisms, and content filtering aligned with responsible AI principl
• es.Ensure compliance with data governance standards, including handling of sensitive data, third-party API integrations, retention policies, and audit loggi

ng.4. Cross-functional Collaboration and Knowledge Trans

• ferCollaborate closely with behavioral scientists, economists, and operational teams to translate research and policy needs into technical syste
• ms.Enable non-engineering staff to contribute safely to AI-assisted development through onboarding, tooling support, and best practic
• es.Communicate technical decisions, risks, and trade-offs through clear documentation suited to an asynchronous, knowledge-driven environme

nt.5. Continuous Improvement and Innovat

• ionEvaluate emerging AI technologies, agentic architectures, and knowledge system approaches beyond traditional retrieval-augmented generati
• on.Identify and address technical debt, balancing rapid delivery with long-term system sustainabili
• ty.Maintain awareness of the evolving AI and engineering landscape, proactively introducing tools and practices that enhance productivity and output quali

ty.
Selection Crit

eria1. Education and Experi

• enceMaster’s degree in Computer Science, Software Engineering, Information Systems, or a related field with at least 5 years of relevant experience; or Bachelor’s degree with at least 7 years of relevant experience; or equivalent combination of education and experie
• nce.Demonstrated track record of taking AI applications from prototype to production at sc

ale.2. Backend and Systems Enginee

• ringStrong proficiency in Python and Node.js or TypeScr
• ipt.Experience designing and operating production APIs (REST, GraphQL, MCP serve
• rs).Solid understanding of distributed systems (queues, retries, idempotency, asynchronous processi
• ng).Experience with relational and non-relational databases, including vector sto
• res.Proven ability to convert prototypes into production-grade syst

ems.3. Cloud Architecture and Production Operat

• ionsDeep experience with cloud platforms (AWS, Azure, or GCP), including containerization, orchestration, autoscaling, and CI/CD pipeli
• nes.Strong observability practices (logging, metrics, distributed traci
• ng).Experience managing production systems, including incident response, capacity planning, and cost optimizat
• ion.Preference for managed, scalable infrastructure in lean team environme

nts.4. Applied AI and Knowledge Sys

• temsHands-on experience integrating LLM APIs (e.g., OpenAI, Anthropic, open-source models via vL
• LM).Strong expertise in context engineer
• ing:Retri
• evalAgentic memory (working, episodic, seman
• tic)Prompt caching and long-context strate
• giesFamiliarity with hybrid search, knowledge graphs, and advanced knowledge syst
• ems.Experience designing evaluation frameworks (gold datasets, LLM-as-judge, uncertainty estimati

on).5. AI Security and Responsibl

• e AIExperience mitigating AI-specific risks (prompt injection, exfiltration, misu
• se).Knowledge of guardrails, structured outputs, and content filter
• ing.Exposure to red-teaming AI systems or contributing to AI risk assessme
• nts.Familiarity with responsible AI principles, including transparency and calibrat

ion.6. Data Governance and Pri

• vacyKnowledge of data protection frameworks (e.g., GDPR, OECD principl
• es).Experience handling PII, implementing data minimization strategies, and designing retention polic
• ies.Ability to assess third-party API data flows and implement audit mechani

sms.7. AI-Assisted Development and Code Re

• viewDaily fluency with agentic coding tools (e.g., Claude Code, Cursor, Codex C
• LI).Strong ability to rigorously review AI-generated c
• ode.Experience working in environments where non-engineers contribute code, with a demonstrated ability to enable contributions without compromising qual
• ity.Balance between rapid iteration and disciplined engineering standa

rds.8. Cross-functional Collabora

• tionExperience working in multidisciplinary teams (research, policy, or operatio
• ns).Excellent written communication skills in document-driven environme
• nts.Ability to translate technical trade-offs into outcomes-oriented language for senior stakehold
• ers.Track record of producing technical documentation, runbooks, and decision reco

rds.
Deliver

ablesThe Software Engineer (Applied AI) is expected to del

• iver:Production-ready AI-enabled platforms and infrastru
• ctureEngineering standards and documentation frame
• worksSecure, compliant, and scalable AI sy
• stemsEvaluation pipelines and quality assurance mecha
• nismsCapacity-building support for non-engineering contrib

utors
Reporting and Collabo

rationThe consultant will work under the supervision of the eMBeD leadership team and collaborate closely with behavioral scientists, economists, and operational teams across the World

Bank.
Please submit your CV and cover letter to embed@worldbank.org by May 15