Software Engineer III

 Software Engineer - III  About the Role  GHX is building a next-generation Intelligent Process Automation (IPA) platform powered by LLMs and AI-native document understanding. We extract structured data from complex healthcare procurement documents — Purchase Orders, invoices, contracts — at scale across cloud environments. As a member of the IPA engineering team, you will bridge strong software engineering with applied AI. You will design and ship Python services, integrate LLM APIs, build AI agents, create skills and validate the output of LLMs to build document extraction pipelines, and own evaluation infrastructure that ensures production quality. This is not a research role — it is a hands-on engineering role where AI fluency amplifies solid software craft.  Core Responsibilities  Python Development & Automation  Build and maintain Python-based automation services and IPA workflows  Develop platform-agnostic solutions supporting future migration across automation tooling  Build reusable libraries, frameworks, and components for automation projects  Integrate automation solutions with REST APIs and enterprise applications  Deploy and monitor automation bots on AWS (Lambda, ECS, SQS, S3)  AI & LLM Integration  Integrate LLM APIs (like Anthropic Claude, OpenAI, Azure AI) into production pipelines  Design classification and extraction prompts for diverse document types (POs, invoices, contracts)  Write prompts that function as formal specifications — unambiguous, edge-case-aware  Build and iterate few-shot, chain-of-thought, and structured output templates  Own prompt library versioning, rollback strategy, and prompt lifecycle management  AI & LLM Integration  Integrate LLM APIs (like Anthropic Claude, OpenAI, Azure AI) into production pipelines  Design classification and extraction prompts for diverse document types (POs, invoices, contracts)  Write prompts that function as formal specifications — unambiguous, edge-case-aware  Build and iterate few-shot, chain-of-thought, and structured output templates  Own prompt library versioning, rollback strategy, and prompt lifecycle management  Document Processing & IDP  Implement OCR/IDP workflows to extract and validate structured and unstructured data  Build confidence scoring frameworks for extracted fields with multi-factor validation  Design and curate ground truth datasets for classification and extraction tasks  Build automated evaluation pipelines tracking precision, recall, and field-level accuracy  Validate model outputs against intent — catch what is technically correct but conceptually wrong  Software Engineering  Design and build production-grade APIs and services around LLM capabilities  Apply Clean Architecture or equivalent — design for testability and maintainabilit...