Design and develop backend services and APIs that support AI-powered applications.
Build, experiment with, and improve AI agents and multi-agent workflows.
Integrate Large Language Model (LLM) providers and AI services into production systems.
Contribute to building Retrieval-Augmented Generation (RAG) pipelines using vector databases and retrieval frameworks.
Work on prompt design, prompt optimization, and prompt strategies to improve response quality and reliability.
Help develop evaluation pipelines to measure LLM performance, reliability, and cost.
Collaborate on the architecture of AI platforms and services that support high-scale workloads.
Implement observability and monitoring for AI systems, including tracing, latency, and cost tracking.
Write clean, maintainable, and testable code while contributing to code reviews and engineering best practices.
Support CI/CD workflows and deployment processes for AI-powered services.

Experience developing backend applications or APIs using languages such as Python, C#, Java, or similar.
Exposure to LLM-powered applications, AI agents, or generative AI systems.
Familiarity with prompt engineering and prompt design techniques.
Experience integrating LLM APIs or AI services (OpenAI, Gemini, or similar).
Knowledge of modern backend frameworks and API development.
Understanding of async programming, distributed systems, or microservice architectures.
Experience with evaluation, experimentation, or benchmarking of AI models.
Strong problem-solving skills and an interest in exploring new technologies.

AI Engineer / AI Developer

Key skills