- Hyderabad, Telangana, India
- Senior
- 5–9 years
The role focuses on advanced prompt engineering, foundation model optimization, and programmatic evaluation of LLM applications for financial services and healthcare sectors.
Responsibilities
- Programmatically generate, test, and evaluate prompt performance at scale using Python.
- Manage foundation model behaviors (GPT-4, Llama, Claude, Mistral), context window dynamics, and tokenization mechanics.
- Implement output validation libraries (Pydantic, Instructor) and guardrail systems.
- Focus on edge-case mapping, deterministic output formatting, and cost optimization.
- Apply advanced prompting techniques such as Few-Shot Prompting, Chain-of-Thought (CoT), ReAct, and Context Engineering.
Requirements
- Nice to have: Few-Shot Prompting
- Nice to have: Chain-of-Thought (CoT)
- Nice to have: ReAct
- Nice to have: Context Engineering