EngineerJobs.io
← Back to all jobs

Job Description

Halliburton is building production-grade AI agents to streamline engineering and operations workflows, and it needs an AI Engineer on the Data & AI team to help turn real processes into reliable agent experiences. You will work within an established agent platform spanning Databricks and Azure, extending it with connectors, evaluation, monitoring, and adoption tracking to support day-to-day use.

This is an onsite role in Houston, Texas, with a requirement of 4+ years of production software experience. The position focuses on end-to-end delivery, including proving agent reliability and ensuring agents remain effective after launch.

Responsibilities

  • Ship workflows that get used: Translate engineering and operations workflows into production agents on the platform, owning the work from initial conversation through daily adoption.
  • Work with the people doing the work: Partner with subject-matter experts to understand how work actually happens, then refine scope until a useful workflow is live.
  • Connect agents to the business: Implement secure tool and data connectors, including MCP servers, to provide governed access to Halliburton data and engineering applications.
  • Prove reliability: Use platform evaluation and tracing to demonstrate agent reliability, then measure adoption and time saved in production.
  • Keep agents on track: Build optimization routines and monitoring to detect drift, regressions, and failures early.
  • Use AI to build AI: Work AI-first every day, leveraging coding agents to move from idea to working agent quickly.
  • Own what you ship: Fix issues as they arise and improve agents based on how users adopt them.
  • Add capabilities to the platform: Contribute templates, connectors, or evaluation components when gaps appear to accelerate future workflow delivery.

Requirements

  • 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, with comfort working across the stack (APIs, services, and simple internal user interfaces).
  • Experience shipping LLM-powered agents to real users, ideally multi-agent systems (not only single prompt chains), including tool calling, RAG, structured outputs, and prompt/context engineering.
  • Hands-on experience with agent frameworks and protocols (examples: LangGraph, Microsoft Agent Framework / Semantic Kernel, OpenAI Agents SDK, Model Context Protocol) and the ability to choose appropriately when a framework is or is not needed.
  • Experience testing non-deterministic systems, including eval sets, automated scoring, and regression checks.
  • Solid engineering fundamentals: Git, automated testing, CI/CD, containers, and cloud deployment.
  • Hands-on Azure experience, including components such as Microsoft Foundry (Azure AI Foundry) Agent Service, Azure OpenAI, Azure AI Search, Azure Kubernetes Service, Container Apps, and Entra ID.

Technologies

  • 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: contributions to SDKs, internal platforms, or shared libraries used by other engineers
  • Total ownership: taking work from idea to production and staying accountable for outcomes beyond a single component
  • Open source: contributions to AI or developer tooling projects
  • Energy or industrial exposure: helpful (not required), with domain training provided

What Success Looks Like

  • First 30 days: Build on the platform and agree on a first workflow and its success measure with a business owner.
  • First 90 days: Ship the first workflow and have it in regular use by the team it was built for, with a measured result such as hours saved.
  • First 6 months: Have several workflows live and in daily use, with additions to the platform helping other builders ship faster.

Similar Jobs