AI Engineer Team/Project Lead
Job Description
Halliburton is hiring an AI Engineering Team/Project Lead to build production AI agents for engineering and operations workflows on an established Databricks and Azure platform.
- Hands-on technical leadership on a project team of three engineers
- Write production code every day and tackle the hardest technical problems
- Turn real engineering and operations workflows into production agents on the platform, from first conversation through daily use
- Collaborate with business stakeholders and delivery partners to define requirements, cut scope, and keep a roadmap focused on highest value
- Define agent architecture for the team’s workflows
- Review designs and code, maintaining high standards for reliability, security, and maintainability
- Implement secure tool and data connectors (including MCP servers) for governed access to Halliburton data and engineering applications
- Use platform evaluation and tracing to demonstrate agent reliability
- Track adoption and time saved after launch in production
- Build optimization routines and monitoring to catch drift, regressions, and failures early
- Establish AI-first development practices: coding agents, shared templates, and code reviews
- Continuously fix issues and improve agents based on real-world use
- When gaps appear, contribute the template, connector, or evaluation artifact that enables the next workflow to ship faster
Requirements
- 6+ years building and shipping production software, or equivalent demonstrated work
- Degree in Computer Science, Data Science, or a related technical field, or equivalent experience
- Experience leading technical work for a small engineering team (architecture, code review, mentoring) while staying hands-on
- Track record partnering with business stakeholders to convert ambiguous needs into clear requirements and a delivery roadmap
- Strong Python; comfort across the stack including APIs, services, and simple internal user interfaces
- Shipped LLM-powered agents to real users, ideally multi-agent systems (tool calling, RAG, structured outputs, and prompt/context engineering)
- Hands-on agent frameworks and protocols (examples: LangGraph, Microsoft Agent Framework / Semantic Kernel, OpenAI Agents SDK, Model Context Protocol (MCP)) and judgment to choose appropriately
- Experience testing non-deterministic systems using eval sets, automated scoring, and regression checks
- Solid engineering fundamentals: Git, automated testing, CI/CD, containers, and cloud deployment
- Hands-on Azure experience, including one or more: Microsoft Foundry (Azure AI Foundry) Agent Service, Azure OpenAI, Azure AI Search, Azure Kubernetes Service, Container Apps, and Entra ID
Technologies
- Python
- Databricks
- Azure (Databricks and Azure)
- MCP servers; Model Context Protocol (MCP)
- LangGraph
- Microsoft Agent Framework
- Semantic Kernel
- OpenAI Agents SDK
- Tool calling
- RAG
- Structured outputs
- 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
- Coding agents
Nice to have
- Databricks: Mosaic AI Agent Framework / Agent Bricks, MLflow tracing and evaluation, Unity Catalog, Model Serving, Vector Search
- Developer tooling contributions: SDKs, internal platforms, or shared libraries used by other engineers
- Total ownership: accountability from idea to production outcomes
- Open source contributions to AI or developer tooling
- Energy or industrial exposure (helpful; not required)
Success looks like
- First 30 days: learn the platform and team; align on first workflow, its success metric, and an initial roadmap with business stakeholders
- First 90 days: ship the team’s first workflow in regular use; measure results such as hours saved; contribute a meaningful share of the code
- First 6 months: several workflows live and in daily use; stakeholders trust the roadmap; architecture and review standards enable faster shipping
Location: Houston, Onsite (Texas)