Principal AI Engineer
Agentic Ai Engineer
Ai Agent Platform
Ai Ml
Application Security
Artificial Intelligence
Automation
Azure Ai
Azure Ai Search
Azure DevOps
CI/CD
Cloud
Cloud Engineer
Cloud Infrastructure
Cloud Native
Cloud Native Technologies
Cloud Platform
Cloud Platforms
Cloud Platforms Cloud Platforms
Cloud Technology
Data Analysis
Data Processing
Databricks Mlflow
DevOps
Devops Tools
DevSecOps
Engineering
Engineering Software
Generative AI
Infrastructure
Infrastructure As Code
Kubernetes
Microsoft Azure
Microsoft Azure Ai
Microsoft Azure Ai Foundry
Platform Engineering
Programming
Programming Language
Security Automation
Security Devops
Software Development
Software Engineering
Job Description
Meaningful work with leaders who care, built for flexibility, and driven by a company that gives back. In this onsite role in Dallas, you will help Hearst’s Homecare Homebase team build and operate a greenfield AI agent platform on top of a production codebase, then mentor teams to adopt it across the organization. The work blends hands-on engineering in .NET and Azure with agentic/orchestration tooling, evaluation, safety and operational quality for regulated data.
What you’ll build and operate
- Design, write, and operate an agent platform that runs autonomously against a production codebase, moving from specification through pull request with human review.
- Implement agentic patterns, orchestration, and tool integration for real-world engineering workflows.
- Make the platform effective across the full technology stack, not only one language or framework.
- Define agent templates and a shared framework that teams can use.
- Own the AI lifecycle from concept through deployment, operation, and iteration on Azure and Azure AI Foundry.
- Shape how work is handed to agents and how results are reviewed from concept through specification and pull request.
- Partner with application teams to integrate AI capabilities into existing products and workflows.
Platform capabilities and governance
- Build APIs, SDKs, MCP servers, and extension points for engineering teams.
- Establish how MCP servers, tools, and agent skills are packaged, versioned, discovered, and distributed, such as via an internal registry or catalog with access controls.
- Design tool access with per-tenant data scoping so agents for one agency can reach only that agency’s data.
- Design context, skills, and retrieval patterns for large codebases, including an application-level knowledge map that links tickets to modules and impact.
- Decide when retrieval is the right tool versus when curated context is better.
- Set versioning, review, and governance for shared AI assets.
Quality, safety, and operational excellence
- Build evaluation frameworks to measure output quality and detect regressions.
- Define guardrails, failure handling, and human-in-the-loop controls for regulated environments, including keeping PHI out of agent context, prompts, and logs.
- Monitor and optimize reliability, accuracy, and cost efficiency using token budgets, rate limits, retry caps, and step limits.
- Establish observability best practices across supervised and autonomous AI usage.
Mentorship and technical direction
- Mentor engineers across the organization and raise AI engineering capability at scale by building working examples in their codebases.
- Define engineering standards and shape the AI technical roadmap with the CTO.
- Evaluate emerging capabilities in LLMs, agentic AI, RAG, and MCP, and bring what proves out into production.
- Advise on build, buy, and partner decisions across the AI toolchain.
- Maintain a working view of commercial and open-weight models and match model tiers to tasks by cost, latency, quality, and data-handling terms.
Required qualifications
- Bachelor’s or advanced degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
- 10+ years in software engineering with recent hands-on coding (you write code today, not only review it).
- 3+ years building and operating production AI systems where agents call tools or change code (RAG or machine learning products alone do not meet this bar).
- Proficiency in Python and modern AI tooling (for example LangChain, LangGraph, MCP, OpenAI, and Anthropic SDKs).
- Hands-on experience building MCP servers or equivalent tool interfaces, including authentication and per-tenant access control.
- Ability to make agents effective across multiple languages and technology stacks, not only one.
- Hands-on experience deploying and operating AI workloads in cloud environments (Azure preferred).
- Solid grasp of LLMs, generative AI, agentic patterns, and context engineering.
- Proven RAG experience and judgment on when retrieval beats curated context.
- Experience with AI evaluation and observability, including quality measurement, cost and token management.
- Working knowledge of handling regulated data such as PHI in AI systems.
- Demonstrated record of mentoring engineers and raising technical capability across teams.
- Evidence of your own work: a repository, code sample, or demo of agent or MCP work that you personally built.
Technologies you’ll work with
- .NET, Azure, Azure DevOps, Kubernetes, Azure AI Foundry
- MCP and MCP-based tooling
- Python, LangChain, LangGraph, OpenAI, Anthropic SDKs
- Vector databases (pgvector, Pinecone, Azure AI Search)
- MLflow, LangSmith, CI/CD
- Cursor, Claude Code, A2A
- A2A
Success looks like
- Within your first 90 days, a working agent template and shared framework that engineering teams can adopt, with at least one team using it on real tickets.
- Telemetry in place for token spend, agent launch frequency, and traceable tool calls.
- A baseline for measuring impact on development process: time saved, delivery velocity, and cost.
- One common standard across teams such as clinical, revenue cycle, and integration, so each team owns its knowledge without building its own agents, models, or tiers.
Preferred qualifications
- Experience integrating AI into C# and .NET applications.
- Experience using AI coding tools such as Cursor or Claude Code on large codebases.
- Familiarity with vector databases and retrieval tooling (for example pgvector, Pinecone, Azure AI Search).
- Exposure to LLMOps and evaluation tooling (for example Azure AI Foundry, MLflow, LangSmith, CI/CD).
- Familiarity with agent-to-agent communication standards such as A2A, and judgment on when a multi-agent design is warranted over a single agent with tools.
- Experience with large legacy codebases and incremental modernization.
- Interest in healthcare, EHR, or revenue cycle applications.
Benefits and what you can expect
- Competitive pay, robust benefits, and professional development opportunities.
- Meaningful work.
- Leaders who care.
- Flexibility.
- A company that gives back.
Work authorization
This position does not provide immigration sponsorship. Applicants must have the right to work in the U.S. without immigration sponsorship.