Key Responsibilities:
Design prompt templates for LLMs across classification, Q&A, generation, and reasoning tasks
Develop modular agent workflows with decision branches and fallback logic
Conduct prompt evaluation experiments for accuracy, reliability, and UX
Work closely with domain SMEs to map business processes into agent logic
Monitor and iterate based on user interaction and model performance
Required Skills:
Strong grasp of NLP and generative AI principles
Familiarity with prompt engineering tools and frameworks (e.g., PromptLayer, LangChain)
Experience working with OpenAI, Claude, or open-source LLMs
Attention to language detail, edge cases, and explainability
Understanding of process flows in industries like insurance, lending, or compliance
