وصف الوظيفة
في Globant، نحن نعمل لجعل العالم مكانًا أفضل خطوة بخطوة. نطور فرص التطوير الأعمال والحلول المؤسسية لإعدادها لمستقبل رقمي. مع فريق متنوع وموهوب موجود في أكثر من 30 دولة، نحن شركاء استراتيجيون لشركات عالمية رائدة في تحويل عملياتها التجارية.
نحن نبحث عن مهندس ذكاء اصطناعي قيادي يشاركنا شغف الابتكار والتحول. هذا الدور حاسم في بناء حلول ذكاء اصطناعي متقدمة تُمكِّن شركائنا التجاريين من التطور وتلبية الطلب المتزايد على تجارب رقمية شخصية وذكية.
المسؤوليات الأساسيةهندسة أنظمة الذكاء الاصطناعي والوكيلتنظيم متعددة العوامل: بناء وتحسين الوكيل الفائق لذكاء CFO، وكلاء فرعيين متخصصين، خطوط لتصنيف النوايا، منطق توجيه الأدوات، وذاكرة الجلسة.
فرض السياسة الحتمية: بناء وصيانة طبقة بوابة الأدوات للتحقق من جميع الإجراءات المولَّدة بواسطة LLM وفق سياسات مصرفية صارمة، مع ضمان عدم وجود معاملات وهلس.
RAG والحوائط الخادمة: تصميم خطوط معالجة RAG من البداية للنهاية (الاستيعاب، فهرسة المتجهات، تحسين الاسترجاع). تطبيق حواجز برمجية (
Job description
At Globant, we are working to make the world a better place, one step at a time. We enhance business development and enterprise solutions to prepare them for a digital future. With a diverse and talented team present in more than 30 countries, we are strategic partners to leading global companies in their business process transformation.
We are seeking a Lead AI Engineer who shares our passion for innovation and transformation. This role is critical in building advanced AI-driven solutions that enable our business partners to evolve and meet the growing demand for personalized, intelligent digital experiences.
Key ResponsibilitiesAI & Agent System EngineeringMulti-Agent Orchestration: Build and refine the AI CFO super-agent, specialist sub-agents, intent classification pipelines, tool routing logic, and session memory.
Deterministic Policy Enforcement: Build and maintain the Tool Gateway layer to validate all LLM-generated actions against strict banking policies, ensuring zero hallucinated transactions.
RAG & Guardrails: Engineer end-to-end RAG pipelines (ingestion, vector indexing, retrieval optimization). Implement programmatic guardrails ("Trust Dial" logic for autonomous vs. approval modes).
AI Evaluation Frameworks: Design automated continuous evaluation pipelines to detect behavioral regressions and hallucination risks before releases reach staging or production.
Cloud-Native & Performance EngineeringBuild resilient, containerized, stateless microservices on Kubernetes designed for high concurrency and horizontal scaling.
Optimize LLM inference layers (token budget management, streaming responses, prompt caching, model fallbacks).
Engineer real-time event streaming pipelines (via Kafka/AWS MSK) for proactive banking triggers.
Implement deep observability using OpenTelemetry, Prometheus, and Grafana for full auditability of agent reasoning chains.
Banking Integration & SafetyBuild robust API adapter layers connecting the AI platform with core banking systems, incorporating retry logic, rate limiting, and idempotency keys.
Implement legacy service facades and secure transaction safety nets (rollback mechanisms, duplicate transaction detection, and reconciliation).
Enforce enterprise security protocols (mTLS, OAuth 2.0, secret rotation).
Engineering Leadership & StandardsSet and enforce code quality, test coverage, and definition-of-done criteria across four delivery pods.
Lead the AI engineering community of practice (architecture syncs, reusable libraries, design pattern documentation).
Mentor engineers on production AI design practices and sign off on release quality gates.
Core Tech StackLanguages: Python, TypeScript, Dart (Flutter dynamic UI context)
AI/LLM: Anthropic Claude (Haiku / Sonnet), LangGraph or custom agent frameworks
Data & Search: pgvector, Pinecone, PostgreSQL, Redis
Streaming & Messaging: Apache Kafka / AWS MSK
Cloud & DevOps: Kubernetes (EKS/AKS), Terraform/CDK, GitHub Actions CI/CD
Observability: OpenTelemetry, Prometheus, Grafana
Requirements & QualificationsMust-Haves:7+ years of overall software engineering experience with a strong track record of shipping complex, high-traffic production systems.
3+ years of hands-on experience building and deploying production-grade LLM/Agentic AI systems at scale (orchestrator/worker patterns, tool calling, RAG pipelines, prompt safety).
Deep expertise in Python and/or TypeScript with solid software design principles (distributed systems, concurrency, fault tolerance).
Proven track record deploying containerized workloads using Kubernetes on major cloud providers (AWS/Azure/GCP) using IaC tools like Terraform or CDK.
Direct experience with system performance tuning, latency budgets, caching strategies, and event-driven architectures (Kafka).
Demonstrated technical leadership experience as a Lead/Staff Engineer conducting rigorous code reviews and setting quality standards.
Nice-to-Haves:Direct experience within Banking, Fintech, or Financial Services, especially integrating with core banking APIs, payment rails, or card platforms.
Familiarity with financial compliance and security standards (PCI-DSS, SOC 2, zero-tolerance data correctness).
Location: Dubai, UAE
Create with us digital products that people love. We will bring businesses and consumers together through AI technology and creativity, driving digital transformation to impact the world positively.
We may use AI and machine learning technologies in our recruitment process. Compensation is determined based on skills, qualifications, experience, and location. In addition to competitive salaries, we offer a comprehensive benefits package. Learn more about our commitment to diversity and inclusion and Globant’s Benefits.