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
Engineer
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
Join Hearst in Dallas, TX (onsite) to build and operate a greenfield AI agent platform on top of an existing production codebase for Homecare Homebase. This role blends hands-on engineering with platform ownership: you will design agentic patterns, implement orchestration and tool integrations, and help teams adopt shared frameworks that scale across the stack. If you enjoy building with .NET and Azure while bringing rigorous evaluation, safety, and observability into regulated environments, this is a strong fit.
What you’ll do
- Design, write, and operate an agent platform that runs autonomously against production code, moving from specification to pull request with human review.
- Implement agentic patterns, orchestration, and tool integration for real-world engineering workflows.
- Ensure the platform works effectively across the full technology stack, not only one language or framework.
- Define agent templates and the shared framework teams will use for consistent delivery.
- 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 to specification through pull request.
- Partner with application teams to integrate AI capabilities into existing products and workflows.
- Build the APIs, SDKs, MCP servers, and extension points that other engineering teams can build on.
- Establish how MCP servers, tools, and agent skills are packaged, versioned, discovered, and distributed, including via an internal registry or catalog with access controls.
- Design tool access with per-tenant data scoping so an agent can only reach the data for the agency it is acting for.
- Design context, skills, and retrieval patterns for large codebases, including an application-level knowledge map that tells an agent which module a ticket belongs to and what it affects.
- Decide when retrieval is the right approach versus when curated context is better.
- Set up versioning, review, and governance for shared AI assets.
- 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.
- Mentor engineers across the organization by building working examples directly in their own codebases.
- Define engineering standards and help 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, matching model tiers to tasks based on cost, latency, quality, and data-handling terms.
What we’re looking for
- 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.
- 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 such as LangChain, LangGraph, MCP, OpenAI SDKs, 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.
- Hands-on experience deploying and operating AI workloads in cloud environments (Azure preferred).
- Strong grasp of LLMs, generative AI, agentic patterns, and context engineering.
- Proven RAG experience, plus judgment on when retrieval beats curated context.
- Experience with AI evaluation and observability, including quality measurement and cost/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 work: a repository, code sample, or demo of agent or MCP work you personally built.
Tools you’ll work with
- .NET, Azure, Azure DevOps, Kubernetes, Azure AI Foundry
- MCP and MCP-based tooling, Python, LangChain, LangGraph
- OpenAI and Anthropic SDKs
- pgvector, Pinecone, Azure AI Search
- MLflow, LangSmith, CI/CD
- Cursor, Claude Code, Vector databases
- 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.
- A common standard across teams (clinical, revenue cycle, and integration), so each team owns its knowledge without building its own agents, models, or tiers.
Benefits and culture
- Competitive pay, robust benefits, and professional development opportunities
- Meaningful work
- Leaders who care
- Flexibility
- A company that gives back
Additional details
- Sponsorship: This position does not provide immigration sponsorship. Applicants must have the right to work in the U.S. without immigration sponsorship.