Build and maintain AI applications and agentic workflows using Python, LangChain, and LangGraph.
Develop and integrate tool-augmented LLM pipelines under the guidance of senior engineers.
Implement and maintain reusable AI skills and components.
Apply prompt engineering techniques to improve LLM output quality and consistency.
Build and test AI agents, including designing agent tools, memory, and decision logic.
Contribute to test harnesses and evaluation frameworks to systematically assess AI agent behaviour and quality.
Write and maintain AI-specific tests including unit tests for agent logic, prompt regression tests, and end-to-end workflow tests.
Work closely with the team to understand business requirements and translate them into technical solutions.
Participate in code reviews, testing, and deployment of AI features.
Keep up with developments in the AI space and bring new ideas to the team.