About the role
Department: Product Development About the Role
GHX is building a cutting-edge LLM-powered document understanding platform focused on classification, structured data extraction, and intelligent orchestration at scale.
This is a high-impact AI engineering role where you will own the full lifecycle—from problem framing to production deployment. Initially, you will focus on prompt engineering and evaluation systems, building the quality foundation for AI performance. Over time, the role expands into agent orchestration, system architecture, and migration of rule-based systems to LLM-driven pipelines. A strong foundation in software engineering (5+ years) is essential. This role demands engineering rigor across both traditional system design and AI system behavior.
Core Responsibilities
1. Prompt Engineering
- Design prompts for diverse document classification and extraction tasks
- Treat prompts as formal specifications (precise, structured, and edge-case-aware)
- Develop few-shot, chain-of-thought, and structured output templates
- Manage prompt lifecycle: versioning, testing, and rollback
- Create and maintain ground truth datasets
- Build automated evaluation pipelines (precision, recall, field-level accuracy)
- Identify and resolve conceptually incorrect outputs despite surface correctness
- Design multi-agent workflows for document processing
- Implement tool-use patterns and integrate MCP servers
- Optimize orchestration for scale and efficiency
- Develop production-grade APIs and backend services
- Apply Clean Architecture / DDD principles
- Write maintainable, testable Python code
- Contribute to CI/CD, deployment, and observability systems
- Act as a bridge between business stakeholders and AI systems
- Translate product requirements into technical architectures
- Communicate system behavior, limitations, and quality metrics clearly
Required Skills & Experience
- 5+ years of software engineering experience (Python preferred)
- Advanced prompt engineering and LLM evaluation expertise
- Experience with ground truth dataset design
- Hands-on experience with LLM APIs (OpenAI, Anthropic, Azure AI)
- AI agent orchestration experience
- Strong understanding of Clean Architecture / DDD principles
- REST API development
- Version control (Git), CI/CD practices, containerization
- Experience with AWS or similar cloud platforms
Now (0–6 months): Prompt Engineering & Evaluation
- Design and refine prompts for classification and data extraction
- Build ground truth datasets and evaluation pipelines
- Establish accuracy benchmarks and quality baselines
- Develop multi-agent document processing pipelines
- Integrate MCP-based tools and external service interfaces
- Orchestrate parallel AI workflows
- Own the end-to-end document intelligence architecture
- Lead migration from rule-based to LLM-powered systems
- Define engineering standards and best practices