InsideBoard is the AI platform dedicated to change management. We support adoption and performance at the world's largest companies (Stellantis, General Motors, Michelin, La Poste, Pernod Ricard, and others). As a Solution Engineer, you are the technical bridge between our customers and the platform: you participate in customer workshops, you capture needs, then you use AI-assisted development (Claude Code, Windsurf and our internal agent tooling) to configure, integrate and extend the platform InsideBoard, often in the same week.
This is not a typical software engineer role, and you do not need to master every technology in our stack. You orchestrate AI agents on a well-documented internal ecosystem (API surface, n8n automation, conventions designed for agents). The AI writes most of the code; your job is to know what she's doing, make sure she's doing the right thing, and stop her when she's not. And you carry out customer relations on the technical side.
Your missions
Customer facing (around 50%)
Lead framing and specification workshops with key account clients (in French and English), from kickoff to steering committees (COPIL).
Transform meetings into actionable deliverables: functional specifications, status matrices, wireframes, integration guides, user guides, reports with validated decisions.
Defend trade-offs in front of the client: standard configuration or specific development, target vision or pragmatic solution, and assume responsibility for recommendation.
Respond to security reviews and technical due diligence questions; write root cause analyzes in the event of a production incident.
Platform configuration and data (approximately 50%)
Configure the InsideBoard platform via its administration interface or its APIs: KPIs (formulas, aggregation, frequencies), action plans and coaching programs, challenges, guidance, profile sections, custom fields, forms, notifications, imports of users, departments and tags.
Build and maintain n8n automation workflows: webhooks, scheduled tasks, AI-generated summaries, RAG content pipelines, centralized error alerting to Slack.
Script data operations in Python or TypeScript: mass migrations with dry-run and rollback discipline, license audits, engagement reports, Excel/CSV/SFTP exchanges with client IT departments.
Plug in LLM features for customers: AI-generated performance summaries, OCR pipelines, RAG knowledge bases, agent prompt design.
The profile sought
You don't need to know all the technologies we use. You need enough technical depth to supervise an AI that knows it: understanding its plan, asking the right questions, spotting when it's drifting, and validating the result before it reaches a customer.
Get notified when I release new stuff! ->
Follow @branzel