What are the responsibilities and job description for the Artificial Intelligence Engineer position at SLB?
Position Title: Domain AI Integration Engineer
Employment Type: Full‑Time
Work Location: Houston, TX
Position Summary
The Domain AI Integration Engineer will be responsible for integrating advanced Artificial Intelligence and Generative AI capabilities into the company's domain software systems (e.g. Delfi, Lumi), with a focus on designing and shipping production-grade agentic solutions.
This role requires specialized technical expertise in AI/ML systems, domain knowledge (e.g. geoscience, petroleum engineering), domain foundation models, and enterprise-scale software integration. A strong understanding of domain workflows is highly valued, as the engineer is expected to translate domain problems into effective agentic solutions.
The engineer will collaborate with product teams, domain experts, and the AI Foundation Team to accelerate AI adoption through advanced agentic systems (multi-agent orchestration, reasoning pipelines, compound AI), deploy domain-specific models, and establish robust agent evaluation frameworks.
This position requires highly specialized knowledge consistent with a professional role in computer science, engineering, or a related technical field, combined with applied domain experience in the energy industry.
Key Responsibilities
- GenAI Integration for SLB Digital Products
- Integrate AI Foundation services (FM Hub, Model Ops, AI Workspace, Agent Workspace, GenAI Infrastructure) into SLB digital products such as Delfi and Lumi.
- Develop reusable integration patterns, APIs, and components that enable scalable, production-ready GenAI capabilities across product teams.
- Deliver hands-on enablement — working demos, reference implementations, and workshops — to accelerate GenAI adoption across domain product teams.
- Domain Foundation Model Integration, Deployment & Benchmarking
- Integrate and deploy domain-specific foundation models into domain workflows and product pipelines, ensuring domain-aligned behavior and performance.
- Collaborate with domain teams to define benchmark datasets, evaluation metrics, and acceptance criteria; establish continuous evaluation frameworks to assess model quality, robustness, and domain relevance.
- Support product teams in embedding benchmarking and evaluation into their development and release processes.
- Optimize deployment workflows for inference efficiency and production readiness.
- Domain Agentic Solution Development
- Design and build end-to-end agentic solutions — including multi-agent systems, reasoning pipelines, and tool-use orchestration — that address real domain challenges in geoscience and energy.
- Translate domain expertise into agent architectures that combine foundation models, domain data, and simulation tools into compound AI systems.
- Develop agent evaluation frameworks and serve as an internal reference for advanced agentic solution patterns.
- Advanced degree (MS or PhD) in Geophysics, Geoscience, Petroleum Engineering, Computer Science, Electrical Engineering, Applied Math, or equivalent.
- Experience with AI/ML model integration, deployment, and evaluation.
- Proven experience building and deploying agentic AI systems (multi-agent, tool-use, reasoning pipelines) in production.
- Experience with cloud‑based AI infrastructure, model operations (Model Ops), and scalable service integration.
- Familiarity with geoscience, subsurface, or energy workflows; a strong understanding of domain problems is highly valued and expected for success in this role.
- Ability to work cross‑functionally with product teams, domain experts, and platform engineering groups.
- Strong communication skills, including the ability to deliver technical training and documentation.
- Experience with using foundation models, large language models, domain‑specific AI systems, agentic systems.
- Hands-on experience with domain AI applications: seismic interpretation, reservoir simulation.
- Familiarity with subsurface software platforms.
- Experience building benchmarking pipelines, evaluation frameworks, or automated testing systems for AI models.
- Knowledge of agent‑based AI architectures and domain agent design.