Design and implement LLM-based and agentic AI systems capable of multi-step reasoning and task execution
Build orchestration logic for tool-using agents (function calling, workflows, decision logic)
Develop and optimize prompting strategies for structured and unstructured outputs
Implement document ingestion and extraction pipelines (e.g., PDFs, semi-structured data)
Integrate AI systems with backend services, APIs, and data sources
Handle production concerns such as:
Error handling and fallback strategies
Latency and cost optimization
Monitoring and iteration based on real usage
Collaborate with engineering and product teams to ship AI features end to end.

Bachelor’s degree in computer sciences, information systems, or equivalent technical degree; or equivalent combination of education and experience.
3 + years of professional software development experience, including hands-on experience delivering LLM-based features to production
Strong proficiency in Python
Proficiency in C# is good to have
Experience working with Azure OpenAI or similar managed LLM platforms
Practical experience with:
Prompt engineering
Tool/function calling
Structured output generation
API integration
Solid understanding of how LLM systems behave in production environments
Ability to work effectively in an existing codebase and software architecture
Some experience with agentic or workflow-based AI systems
Familiarity with Retrieval-Augmented Generation (RAG)
Excellent English communication skills, both written and verbal, due to frequent interaction with North American team members.

AI Engineer

Key skills