Description

In this role, you will design and maintain robust backend services for AI applications while collaborating with scientists to ensure smooth transitions from prototypes to production. Your day-to-day responsibilities will involve optimizing model performance and mentoring junior engineers.

Requirements

• •6+ years of professional experience in backend software development
• •Strong proficiency in Golang and preferably Java/Kotlin
• •Experience with cloud platforms (AWS, GCP, or Azure) and containerization technologies (Docker, Kubernetes)
• •Experience building backend systems for complex workflows
• •Familiarity with foundational LLM concepts such as retrieval-augmented generation (RAG)
• •Practical experience developing or managing MCP servers and familiarity with A2A communication protocols
• •Experience with event-driven architecture and message queues (e.g. Kafka)

Tasks

• •Design and maintain scalable backend services for AI applications
• •Apply advanced prompt engineering techniques to enhance model performance
• •Implement model integration patterns for external and internal services
• •Develop communication strategies for Agent-to-Agent (A2A) protocols
• •Manage Conversational Protocols (MCP servers) for stateful interactions
• •Define observability standards for AI applications, including key metrics
• •Implement logging and monitoring tools for diagnosing AI pipeline issues
• •Collaborate with ML and Data Scientists to transition models to production
• •Ensure security, reliability, and performance of production systems
• •Participate in code reviews and architectural discussions
• •Mentor junior engineers and promote best practices in backend development

Tools & Technologies

Benefits