> Markdown version of [/jobs/ext/2661313-principal-software-engineer-contract-ai](https://www.wearedevelopers.com/jobs/ext/2661313-principal-software-engineer-contract-ai). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Principal Software Engineer - Contract AI - **Company:** McKinsey & Company - **Location:** Atlanta, GA, United States - **Experience:** Expert - **Salary:** $214,100.0 - $217,600.0 - **Contract:** Permanent contract - **Skills:** .NET Framework, Artificial Intelligence, Architectural Patterns, Microsoft Azure, C Sharp (Programming Language), Profiling, Software Quality, Code Review, Continuous Integration, Software Debugging, Distributed Systems, Identity and Access Management, Python (Programming Language), PostgreSQL, Object-Oriented Software Development, Open Source Technology, Role-Based Access Control, Secure Coding, Software Engineering, TypeScript, Test-Driven Development (TDD), .NET Core, ReactJS, Large Language Models, Generative AI, Event Driven Architecture, Pytest, AI Platforms, Cosmos DB, Api Design, Restful APIs, Terraform, Sql Tuning, Serverless Computing, Microservices - **Published:** August 2, 2026 - **Apply:** https://diversityjobs.com/main/sendform/8/8/28176/1/17813855?backUrl=%2Fcareer%2F17813855%2FPrincipal-Software-Engineer-Contract-Ai-Georgia-Atlanta ## About the Role * 8+ years of software engineering experience, with a strong portfolio of production systems you architected and shipped * Expert-level Python-application development, async patterns, type-checking, testing frameworks (pytest), performance profiling * Production experience with Generative AI: Azure OpenAI, LangChain, Semantic Kernel, RAG architectures, embeddings, structured output extraction, evaluation harnesses * Strong C#/.NET-OOP design, .NET Core / .NET 8, REST APIs, background services is required * Hands-on experience with agentic AI frameworks in shipped production systems -LangGraph, AutoGen, CrewAI, or equivalents is required * Azure platform depth: AKS, Azure Functions, CosmosDB, Postgres, Azure OpenAI, Azure DevOps, Terraform. Distributed system design: microservices, event-driven architecture, API design, multi-tenant data isolation, observability * Enterprise engineering discipline: TDD, CI/CD, RBAC/IAM, secure coding, SQL performance tuning * TypeScript/React production experience for full-stack coverage * Document understanding: vision LLMs (GPT-4o Vision), OCR, multi-modal extraction pipelines from PDF/DOCX * Familiarity with contract management, procurement, or invoice processing domains * Experience contributing to or consuming open-source AI frameworks * Ability to communicate architecture decisions in writing and in technical reviews; comfort with client-facing technical interaction ## Description You will own extraction and evaluation architecture, design and evolve the multi-stage AI pipeline that converts unstructured contracts and invoices into structured compliance findings -covering document ingestion, vision LLM extraction, clause parsing, normalization, and deterministic evaluation logic. You are the deepest individual technical contributor on the Contract AI platform. You own the hardest engineering problems - extraction model architecture, compliance evaluation logic, pipeline performance at scale, and the agentic reasoning layer. You are not primarily a manager, but you raise the ceiling of what the team can build: through architecture, code, code review, and mentoring. You'll lead GenAI and agentic engineering, build, tune, and productionize agentic workflows for contract analysis using LangGraph, Semantic Kernel, or equivalent frameworks. You will advance the platform's reasoning capabilities beyond single-shot prompting into multi-step, tool-using AI agents. You will set the technical bar for the team: own code quality, architecture reviews, and technical standards. You will be the go-to resource for the hardest debugging, design, and performance challenges. You'll also mentor Senior Software Engineers, drive accuracy at scale, own evaluation accuracy metrics across compliance case categories; design validation harnesses, prompt refinement workflows, and confidence scoring frameworks. You will contribute across the stack, write Python and C# in production; contribute to the React/TypeScript analytics dashboard when needed; and own end-to-end delivery of major platform features from design through deployment. You'll accelerate client deployments, build reusable extractor and evaluator templates that reduce Proof-of-Value configuration time; document architectural patterns for delivery engineers to apply consistently across client environments. You'll stay at the frontier: continuously evaluate emerging agentic frameworks, multi-modal models, and document-understanding approaches; propose and prototype high-value capabilities before they appear in competitors' roadmaps. ## Related Videos - [Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure](https://www.wearedevelopers.com/videos/1532-agentic-ai-from-theory-to-practice-developing-multi-agent-ai-systems-on-azure) - [pytest: Simple, rapid and fun testing with Python](https://www.wearedevelopers.com/videos/213-pytest-simple-rapid-and-fun-testing-with-python) - [Watch Tests Go Brrrr! : Getting Started with Cypress in ReactJS](https://www.wearedevelopers.com/videos/282-watch-tests-go-brrrr-getting-started-with-cypress-in-reactjs) - [Infrastructure as Code: The Developer's Secret Weapon](https://www.wearedevelopers.com/videos/1221-infrastructure-as-code-the-developer-s-secret-weapon) - [Automagic Configuration in Python](https://www.wearedevelopers.com/videos/363-automagic-configuration-in-python) - [Implementing Feature Environments with AWS and Terraform](https://www.wearedevelopers.com/videos/531-implementing-feature-environments-with-aws-and-terraform) ## Related Articles - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this) - [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers) - [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care)