about 12 hours ago
Hyderābād, IndiaSenior / Staff+
Responsibilities
- Design classification and extraction prompts for diverse document types.
- Write prompts that function as formal specifications.
- Build and iterate few-shot, chain-of-thought, and structured output templates.
- Own the prompt library, versioning, and rollback strategy.
- Define and curate ground truth datasets for classification and extraction tasks.
- Build automated evaluation pipelines tracking precision, recall, and field-level accuracy.
- Design multi-agent pipelines for document processing workflows.
- Build production-grade APIs and services around LLM capabilities.
- Contribute to CI/CD, observability, and deployment pipelines.
- Serve as technical contact between business teams and the AI engineering layer.
Requirements
- 8+ years of software engineering experience, preferably in Python and AWS.
- Advanced prompt engineering and LLM evaluation frameworks.
- Experience in ground truth dataset design.
- Familiarity with LLM APIs such as OpenAI, Anthropic, and Azure AI.
- Knowledge of Clean Architecture or Domain-Driven Design.
- Experience in REST API design and Git.
- Familiarity with CI/CD and containerization.