The company is hiring an AI Engineer for its Company Brain project, building agents that put engineering knowledge to work. The first build is a single place to find what the company knows and has decided, plus a set of agents that use that knowledge, starting with the EPC team.
You will work alongside engineers, developers and operators, and take a problem from the first conversation through to production. Within 90 days you will ship a production workflow.
Responsibilities
Build and run the company's multi-gigawatt microgrids work with AI systems that apply power engineering rigor and modern software practice to automate processes.
Work with electrical engineering, development, commercial and operations teams, partnering closely with the CIO.
Own the company brain from first conversation to a system people use daily, and ship the first production agent workflow within 90 days.
Run the company brain: define each agent's job, set its evals, and monitor its dashboards.
Triage failures across the architecture and decide what gets fixed first.
Choose and secure the platform, comparing open-source options such as Cognee with vendor tools, and govern the data, credentials and tool permissions each agent can access.
Sit with engineers, developers and operators to see how work really gets done, and find where AI removes the most manual effort.
Turn vague requests into a scoped problem, a working prototype within days, and a path to production.
Gather requirements before building, ship the smallest useful version first, and avoid tools that grow into overbuilt products nobody uses.
Run hands-on sessions that teach colleagues to use and extend what you build.
Own each system from first prototype to a stable production service others can operate.
Build connectors that pull data from tables, reference sources, meetings, chat, files and email into the knowledge base on a schedule.
Build search, question answering and routing agents over internal sources so documents and decisions reach the right people the same day.
Automate document and permit flow, digests and a company change log.
Build evaluation harnesses with representative data and graders to catch regressions before users do.
Diagnose failures from traces and logs, and weigh fixes against quality, latency and cost.
Turn each deployment into reusable patterns and playbooks.
Requirements
High agency and urgency: you take problems on as your own and move without waiting for permission or a ticket.
Self-directed: you set priorities, pick up new domains and tools quickly, and look for larger scope.
You build with the latest models and agent tooling daily and can show how AI has changed your own work.
You can explain in detail how you solved the hardest problem you have owned, including what failed.
You build trust fast by explaining technical choices clearly to engineers, operators and executives, adjusting depth to the audience.
You keep shipping through setbacks, ambiguity and the limits of a legacy industry.
You want to help modernize how the energy industry builds and runs.
Agentic systems: production experience with models, including tool use, retrieval, memory, structured outputs and multi-step agent workflows.
Working knowledge of agent orchestration and integration, including MCP servers, tool design, context management and human-in-the-loop review.
Experience designing multi-agent architectures: orchestration, triage and routing between agents, token- and cost-efficient context, and secure handling of data, credentials and tool permissions.
A systematic approach to evaluation: golden datasets, regression suites, and LLM-as-a-judge calibrated against human labels.
Observability, guardrails and grounding that let a production agent run with confidence.
Engineering: you write tests, run regression suites and trace failures to their root cause. No specific programming language is required.
Comfort with SQL, data pipelines, cloud services and CI/CD.
Build systems that fail loudly, alerting the right person when an agent breaks rather than failing silently.
4+ years of experience building software. Recent graduates with a strong record of shipped projects are encouraged to apply.
Conditions
Equal opportunity: one short statement at most.
Benefits
Compensation of $175,000 to $230,000 base, depending on experience, plus bonus and equity.
Ownership of major parts of the system end to end, with direct influence on the bottom line.
Work on multi-gigawatt, national-scale infrastructure for AI-scale compute and industrial projects, backed by strong funding.