Keep agents on track- Build optimization routines and monitoring that catch drift, regressions and failures early, so agents keep operating as designed long after launch.
Use AI to build AI- Work AI-first every day with coding agents to get from idea to working agent fast.
Own what you ship- Fix what breaks and keep improving your agents based on how people actually use them.
Add to the platform- When you hit a gap, contribute the template, connector or evaluation that closes it, so the next workflow ships faster.
Who you are
AI-first by default- You reach for an agent before you open a ticket. Your own workflow is already heavily automated, and you can show us how.
A builder with high agency- You don't wait for a perfect spec. You get the smallest useful version live fast, then harden and expand it.
Allergic to repeated work- When you see the same task done twice, you build a tool so nobody has to do it a third time.
Comfortable in the mess- Legacy systems, messy data and shifting requirements don't slow you down.
Results over demos- A demo is not the finish line. You measure success by evaluation results, adoption and demonstrated time savings for the business.
Fluent in business and code- You turn a business problem into a technical plan, then build it yourself.
What you'll need
Requires 4+ years building and shipping production software, or equivalent demonstrated work.
Degree in Data Science, Statistics, Applied Mathematics or a related quantitative field, or an equivalent data science background.
Strong Python, and comfort working across the stack (APIs, services, simple internal user interfaces).
Shipped LLM-powered agents to real users, ideally multi-agent systems rather than single prompt chains: tool calling, RAG, structured outputs, and prompt and context engineering.
Hands-on experience with agent frameworks and protocols (for example LangGraph, Microsoft Agent Framework / Semantic Kernel, OpenAI Agents SDK, Model Context Protocol) — and the judgment to know when not to use one.
Experience testing non-deterministic systems: building eval sets, automated scoring and regression checks.
Solid engineering fundamentals: Git, automated testing, CI/CD, containers and cloud deployment.
Hands-on Azure experience, such as Microsoft Foundry (Azure AI Foundry) Agent Service, Azure OpenAI, Azure AI Search, Azure Kubernetes Service or Container Apps, and Entra ID.
Nice to have
Databricks- Mosaic AI Agent Framework / Agent Bricks, MLflow tracing and evaluation, Unity Catalog, Model Serving, Vector Search.
Developer tooling- You have contributed to SDKs, internal platforms or shared libraries that other engineers use.
Total ownership- You treat what you build as your own. You take it from idea to production and stay accountable for the outcome, not just your piece of it.
Open source- Contributions to AI or developer tooling projects.
Energy or industrial exposure- Helpful, not required. We will teach you the domain; we can't teach you to build.
What success looks like
First 30 days- You are building on the platform and have agreed on your first workflow and its success measure with a business owner.
First 90 days- Your first workflow is shipped and in regular use by the team it was built for, with a measured result such as hours saved.
First 6 months- Several workflows are live and in daily use, and what you added to the platform is helping other builders ship faster.
World Class Benefits
At Halliburton, we're committed to providing you and your family with a comprehensive and affordable benefits package - which means we offer support for your physical, emotional, financial and parental needs, both now and in the future. When you join our team, you'll have access to a wide range of resources designed to help you thrive at work and at home. By clicking here you can review a summary of the benefits available once you join.
Halliburton is an Equal Opportunity Employer. Employment decisions are made without regard to race, color, religion, disability, genetic information, pregnancy, citizenship, marital status, sex/gender, sexual preference/ orientation, gender identity, age, veteran status, national origin, or any other status protected by law or regulation.
Location
Houston, Onsite
Job Details
- Requisition Number: 213137
- Experience Level: Experienced Hire
- Job Family: Engineering/Science/Technology
- Product Service Line: Global R&D
- Full Time / Part Time: Full Time
Compensation Information
Compensation is competitive and commensurate with experience.
Please Note: This posting is intended to collect candidate information for Halliburton’s talent pool, and is not considered an application. By completing the candidate profile, recruiters will have visibility to your information in order to contact you for a future related job opportunity. In addition to providing your information on this posting, we encourage you to create a Job Alert within our career site. The Job Alert allows you to select search criteria for positions that match your interest(s). Once positions are posted that match your search criteria, you will receive an email notification.