AI Engineer, Agent Platform
Agentic Ai
Agentic Ai Engineer
Agentic Ai Engineering
Agentic Ai Platform
Ai Agent
Ai Agent Engineering
Ai Agent Platform
Ai Engineer
Ai Ml
Ai Platform
Ai Security
Artificial Intelligence
Artificial Intelligence Engineer
Azure Ai
Data Analysis
Data Architecture
Data Engineer
Data Integration
Data Pipeline
Data Platform
Data Processing
Data Science
Engineer
Generative AI
Generative Ai Agents
Generative Ai Engineer
Generative Ai Engineering
Information Technology (IT)
Microsoft Azure
Microsoft Azure Ai Foundry
Programming
Programming Language
Programming Languages
Software Development
Software Engineering
Job Description
Halliburton is building production-ready AI agents and is hiring an AI Engineer on the Data & AI team to turn real engineering and operations workflows into agents that people can rely on. You will work with an established agent platform across Databricks and Azure and extend it with connectors, evaluation, monitoring, and adoption tracking for day-to-day use.
What you’ll do
- Ship workflows people actually use by turning real engineering and operations processes into production agents on the platform, then owning the work from first conversation through daily adoption.
- Work closely with domain experts by sitting with the people who do the work, learning the true workflow details, and narrowing scope until a useful version is live.
- Connect agents to business systems using secure tool and data connectors, including MCP servers, to provide governed access to Halliburton data and engineering applications.
- Prove reliability with platform evaluation and tracing so each agent’s behavior is dependable, then track adoption and time saved in production.
- Keep agents stable over time by building optimization routines and monitoring to detect drift, regressions, and failures early.
- Use AI to build AI with AI-first development, including coding agents to move from idea to a working agent quickly.
- Own what ships by fixing issues and improving agents based on how teams use them in production.
- Extend the platform when you find gaps, by contributing templates, connectors, and evaluation components that help future workflows ship faster.
What you bring
- 4+ years building and shipping production software, or equivalent demonstrated work.
- A 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, including APIs, services, and simple internal user interfaces.
- Experience shipping LLM-powered agents to real users, ideally multi-agent systems (not just single prompt chains) with tool calling, RAG, structured outputs, and prompt and context engineering.
- Hands-on experience with agent frameworks and protocols such as LangGraph, Microsoft Agent Framework / Semantic Kernel, OpenAI Agents SDK, and Model Context Protocol, along with judgment about when not to use a given framework.
- Experience testing non-deterministic systems, including building eval sets, automated scoring, and regression checks.
- Solid engineering fundamentals: Git, automated testing, CI/CD, containers, and cloud deployment.
- Hands-on Azure experience, including services such as Microsoft Foundry (Azure AI Foundry) Agent Service, Azure OpenAI, Azure AI Search, Azure Kubernetes Service, Container Apps, and Entra ID.
Technologies you’ll work with
- Python, Databricks, Azure, MCP servers
- LangGraph, Microsoft Agent Framework, Semantic Kernel, OpenAI Agents SDK
- Model Context Protocol, RAG, LLM-powered agents
- Git, CI/CD, containers, cloud deployment
- Microsoft Foundry (Azure AI Foundry) Agent Service, Azure OpenAI, Azure AI Search
- Azure Kubernetes Service, Container Apps, Entra ID
Benefits
- Comprehensive and affordable benefits package supporting physical, emotional, financial and parental needs
- Wide range of resources designed to help you thrive at work and at home
Nice to have
- Databricks: Mosaic AI Agent Framework / Agent Bricks, MLflow tracing and evaluation, Unity Catalog, Model Serving, Vector Search
- Developer tooling: contributing to SDKs, internal platforms, or shared libraries other engineers use
- Total ownership: taking work from idea to production and staying accountable for outcomes
- Open source: contributions to AI or developer tooling projects
- Energy or industrial exposure (helpful, not required)
How success is measured
- First 30 days: build on the platform and agree on the first workflow and its success measure with a business owner.
- First 90 days: ship your first workflow and ensure it is in regular use by the team it was built for, with a measured result such as hours saved.
- First 6 months: multiple workflows are live and in daily use, and what you added helps other builders ship faster.
Location: Houston, Onsite
Company: Halliburton