Senior AI Engineer (Backend-Focused: Agentic Systems & Conversational AI)

Role Summary

We are looking for a Senior AI Engineer with deep backend engineering expertise to join the technology team at Vezeeta. You will design and build the production backend systems that power our AI-driven patient experiences across our healthcare platform.

We need someone who can architect robust microservices, own system reliability, and integrate LLM-based agentic workflows into production at scale.

Key Responsibilities

• Design and build scalable microservices for backend systems and AI workflows.
• Develop high-performance APIs (REST & event-driven) with strong reliability and low latency.
• Integrate AI services with core systems (booking, pharmacy, CRM).
• Own end-to-end delivery of AI features: design → build → deploy → monitor → iterate.
• Build orchestration layers for AI agents (intent detection, tool/function calling, RAG).
• Translate product requirements into scalable AI architectures (LLMs, retrieval systems, rules engines).
• Optimize backend systems and AI pipelines for performance, scalability, cost, and latency.
• Perform advanced debugging and performance tuning across systems and AI workflows.
• Implement observability, logging, and monitoring for production AI systems.
• Build feedback loops from real user interactions to continuously improve model behavior.
• Define and implement evaluation frameworks for quality, accuracy, and safety.
• Optimize prompts, retrieval systems, and agent logic for efficiency and reliability.
• Write clean, maintainable, and well-tested code following best practices.
• Lead design of scalable, fault-tolerant AI infrastructure and contribute to technical strategy.
• Stay current with backend and AI advancements and share knowledge with the team
  
  

Requirements

Experience & Skills:

• 5+ years in backend engineering with strong system design experience.
• Strong proficiency in C#, .NET, and Python.
• Experience building microservices and RESTful APIs at scale.
• Solid database knowledge (SQL Server, PostgreSQL, MySQL).
• Strong understanding of OOP, design patterns, and distributed systems.
• Experience with Git, CI/CD, and deployment practices.
• Hands-on experience with Docker and Kubernetes.
  
  

AI / ML Expertise

• Experience building LLM-powered systems and agentic workflows.
• Strong knowledge of RAG pipelines, vector databases, and retrieval systems.
• Familiarity with prompt engineering, evaluation, and safety guardrails.
• Experience optimizing LLM usage (latency, cost, caching).
• Experience with observability tools for AI systems.
  
  

Infrastructure

• Experience with cloud platforms (preferably AWS: Lambda, S3, SNS, SQS).
  
  

Education

• Bachelor’s or Master’s in Computer Science or related field.
  
  

Soft Skills

• Strong cross-functional collaboration across engineering, product, and business teams.
• Excellent time management and prioritization in fast-paced environments.
• Ability to thrive in agile, dynamic environments with evolving requirements.
• Clear communication and stakeholder alignment skills.
• High ownership mindset with a proactive approach to problem-solving and delivery
  
  

What Makes This Role Unique?

• Be a founding engineer on a new AI-driven venture within Vezeeta, shaping both the product and technical direction from day one.
• Own the end-to-end architecture of AI systems in production, not just prototypes or experimentation.
• Work at the intersection of healthcare, backend engineering, and applied AI, solving real patient problems at scale.
• High ownership and visibility—partnering directly with leadership on strategy and execution.
• Opportunity to build agentic AI systems that directly impact user experience and business outcomes.