Senior Software Engineer II - AI Platform

About the Company

Careem is building the Everything App for the greater Middle East, making it easier than ever to move around, order food and groceries, manage payments, and more. Careem is led by a powerful purpose to simplify and improve the lives of people and build an awesome organisation that inspires. Since 2012, Careem has created earnings for over 2.5 million Captains, simplified the lives of over 70 million customers, and built a platform for the region’s best talent to thrive and for entrepreneurs to scale their businesses. Careem operates in over 70 cities across 10 countries, from Morocco to Pakistan.

About The Team

The AI Acceleration Office builds the intelligence layer that powers Careem’s ecosystem, and we are looking for a Senior Software Engineer to drive architecture and development of it. Our mission is to drive competitive value through an Agentic AI Platform, a system that can design, orchestrate, and manage autonomous AI agents across customer and operational journeys.

About The Role

As a Senior Software Engineer, you’ll lead the architecture and development of the AI Agent Creation and Management Platform, an intelligent layer that enables scalable agent creation, orchestration, lifecycle management, and performance monitoring. You’ll work across backend systems, AI infrastructure, and data orchestration, designing abstractions that connect LLMs, context, memory, and state into real-time adaptive agents. This is a hands-on leadership role, you’ll design systems, ship code, mentor engineers, and influence Careem’s long-term AI platform strategy.

What You’ll Do

• Architect and implement the foundational services for Careem’s Agentic AI Platform, covering agent creation APIs, orchestration pipelines, state machines, and monitoring layers.
• Design abstractions for multi-agent collaboration, memory persistence, and reasoning cycles integrated.
• Build scalable orchestration frameworks (LangGraph, or custom) that coordinate model calls, context injection, and multi-turn workflows across internal and external agents.
• Develop observability and governance systems for AI agents: tracing, metrics, auditing, and self-healing.
• Integrate LLM-based and retrieval-augmented components into backend services with strict latency, reliability, and compliance requirements.
• Work with data scientists and ML engineers to operationalize models (embedding stores, vector databases, evaluation pipelines, model versioning).
• Establish standards for agent safety, lifecycle management, and deployment reliability across Careem’s product ecosystem.
• Mentor engineers and shape platform-wide engineering practices around AI integration and distributed systems design.
  
  

• 6+ years of backend or distributed systems engineering experience, with 2–3 years in AI/ML infrastructure or LLM-based systems.
• Deep hands-on experience in Python and Go, with production experience in building scalable, event-driven architectures.
• Expertise in orchestration and distributed compute (Kubernetes).
• Experience in building end-to-end event-drive architecture and data pipelines (Kafka, Airflow and Flink)
• Familiarity with agentic frameworks (LangGraph, LangChain, AutoGen) and design of multi-agent or RAG systems.
• Experience in integrating LLMs and vector stores (FAISS, Pinecone, Weaviate, Milvus) into backend applications.
• Solid understanding of model and agent observability, monitoring, and continuous evaluation.
• Strong architectural skills, capable of designing systems that balance scalability, cost, and experimentation velocity.
• Experience working with data streaming, metrics, and real-time feedback loops.
• Growth mindset and bias for ownership, you thrive in high-autonomy, fast-paced, and purpose-driven environments.
  
  

• Work and learn from great minds by joining a community of inspiring colleagues.
• Put your passion to work in a purposeful organisation dedicated to creating impact in a region with a lot of untapped potential.
• Explore new opportunities to learn and grow every day.
• Work 4 days a week in office & 1 day from home, and remotely from any country in the world for 30 days a year with unlimited vacation days per year. (If you are in an individual contributor role in tech, you will have 2 office days a week and 3 to work from home.)
• Access to healthcare benefits and fitness reimbursements for health activities including gym, health club, and training classes.