Principal AI Engineer - LLM/Agents
SB Energy
| Company | SB Energy |
| Category | Engineering |
| Location | California |
| Remote | On-site (inferred) |
| Employment | Not stated |
| Level | Lead |
| Salary | Not stated by the employer |
| Posted | 22 May 2026 |
| Last verified | 12 Aug 2026 |
| Source | Employer ATS (greenhouse) |
Description
Do you want to work with high-caliber professionals in a dynamic and growing company? Are you entrepreneurial, hard-working, and collegial? Join us at SB Energy, a leading infrastructure company backed by SoftBank Group and Ares Infrastructure, pairing cutting-edge innovation with best-in-class execution. Our mission is to deliver reliable and secure data center and power infrastructure to strengthen America's future.
Founded in 2019, SB Energy is a SoftBank Group company headquartered in Redwood City, California. In 2026, SoftBank Group and OpenAI announced a $1 billion investment to support SB Energy as their leading development and execution partner for data center campuses, while Ares Infrastructure continues its long-standing support of the company's growth. SB Energy develops, builds, owns, and operates some of the largest and most technically advanced energy and data center infrastructure projects in the United States. Since its founding, the company has rapidly grown into a top-tier integrated platform with more than 3 gigawatts (GW) in operation and a multi-GW pipeline of energy and data center infrastructure nationwide.
SB Energy also leverages a strong culture of innovation to identify and integrate new technologies into its projects, including its AI-based digital platform, delivering energy infrastructure that is local, reliable, and matched to load. We are building the energy and infrastructure future—today.
Come join us in accelerating the energy and infrastructure transition! Title: Senior AI Engineer – LLM / Agents
Basic Function:
Senior AI Engineer – LLM / Agents will serve as the technical principal for how SB Energy designs, measures, observes, and scales AI-enabled workflows. This role defines how ChatGPT, Codex, custom agents, MCP servers, skills, tools, APIs, structured responses, token and context management, traces, evals, and production observability work together in governed enterprise workflows.
This person will establish reusable architecture, standards, templates, and quality gates so agentic workflows can move from prototype to controlled production use. The role will help SB Energy make workflows measurable, observable, secure, cost-aware, reliable, and auditable across Power Markets, Storage Optimization, Asset Operations, Project Development, Engineering, Finance, HR, and other approved enterprise domains. The AI Engineer owns the cross-domain operating method, evaluation system, observability patterns, and reusable technical standards that allow those workflows to scale with quality.
Responsibilities:
- Define the technical architecture for SB Energy agent workflows, including ChatGPT, ROCstar, MCP, agents, skills, tools, APIs, retrieval, structured outputs, trace metadata, evals, and observability.
- Establish reusable workflow patterns for agent planning, tool calling, data retrieval, exception handling, fallback behavior, escalation, and production support.
- Create standards for skill design, prompt structure, tool descriptions, tool schemas, API response formats, source citation behavior, structured outputs, and workflow handoffs.
- Define token and context management practices, including when to use conversation state, retrieval, file search, cached context, summarization, structured intermediate state, and compressed tool returns.
- Build evaluation frameworks for agent workflows, including gold datasets, regression tests, numerical reconciliation checks, rubric-based grading, tool-call correctness checks, and human feedback loops.
- Lead the design of observability for agents and tools, including workflow logs, cost, latency, token usage, tool success rate, bad-answer rate, eval pass rate, user acceptance, and incident tracking.
- Partner with domain Forward Deployed Engineers to convert high-value workflows into measurable agent systems with explicit inputs, outputs, owners, permissions, evals, runbooks, release gates, and continuous im