AI Engineer

Requirements

• If you think you match at least 70% of these criteria, please apply!
• You have 5+ years of experience in software engineering and a proven track record of shipping production systems
• You have hands‑on experience building LLM-powered features in production, with a clear understanding of the trade‑offs (quality, cost, latency, safety) and how they connect to product and business needs
• You know how to systematically improve LLM systems: versioned prompts, offline/online evaluations, data analysis, and iteration based on real‑world signals
• You can industrialize LLM systems at scale (caching, batching, model routing, observability, rate limiting, ML CI/CD pipelines)
• You are strong in Python and comfortable working with REST APIs and making pragmatic architectural decisions
• You operate as a senior engineer: debugging complex systems, refactoring with intent, reviewing code thoughtfully, and thinking ahead about scalability
• You take ownership: you identify gaps, propose solutions, and go beyond your immediate scope
• You connect technical decisions to product and business outcomes
• You regularly use AI tools in your daily workflow
• You communicate clearly and collaborate effectively, especially with ML teams
• You are fluent in English (written and spoken) and comfortable working in an international environment
• (Desirable) Basic knowledge of Kubernetes and Terraform to independently deploy and operate services
• (Desirable) French is a plus for day‑to‑day collaboration in our Paris office

What the job involves

• You’ll join the Incidents Squad, the team responsible for the full lifecycle of a GitGuardian incident — from detection to remediation
• AI models are involved at every stage, and the team both implements and maintains them
• As a Senior Software Engineer focused on AI/LLM features, you’ll be brought in to improve, scale, and stabilise these capabilities as they transition from early‑stage features to core product workflows
• In your first six months, you’ll get fully acquainted with the existing LLM features, bring your expertise to improve their reliability and stability (quality, latency, robustness, observability), and start suggesting and driving product improvements in close collaboration with the team
• Build and iterate on LLM features, including agentic workflows, using Lang

  Graph and Lang

  Smith
• Scale the platform foundations behind these features — orchestration, performance, and reliability
• Partner closely with the team’s ML Engineer on design, evaluation, and productionisation of AI systems
• Own the AI at the heart of GitGuardian’s core product. The Incidents Squad owns the full lifecycle of a secret leak — creation, prioritisation, remediation — and AI is embedded at every step. You’ll be the engineer making it work reliably at scale
• Work at the intersection of product and ML. You’ll collaborate directly with a dedicated ML Engineer on design, evaluation, and productionisation, bridging the gap between research and production
• Be at the frontier of applied AI. As GitGuardian ships more and more LLM‑based features, you’ll be the person improving their reliability, latency, and robustness as they become core product workflows
• High ownership, senior scope. This is a senior role with real influence on architecture and product direction