AI Engineer

GitGuardian is a global cybersecurity scale‑up based in Paris, New‑York City, and Boston. The company focuses on non‑human identity security, offering end‑to‑end solutions for secrets detection, productivity tools, remediation, observability, and proactive leak prevention. More than 600 000 developers worldwide use GitGuardian’s solutions.

About Your Team And Your Mission

You will join the Incidents Squad, the team responsible for the full lifecycle of a GitGuardian incident – from detection to remediation. The squad implements and maintains AI models involved at every stage, and the team brings expertise to improve reliability and stability of LLM features.

On a Day‑to‑Day Basis, You Will

• Build and iterate on LLM features, including agentic workflows, using LangGraph and LangSmith.
• Scale the platform foundations behind these features – orchestration, performance, and reliability.
• Partner closely with the team’s ML Engineer on design, evaluation, and productionization of AI systems.

Why This Role

• Own the AI at the heart of GitGuardian’s core product. The Incidents Squad owns the full lifecycle of a secret leak, and AI is embedded at every step. You will 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 productionization, bridging the gap between research and production.
• Be at the frontier of applied AI. As GitGuardian ships more LLM‑based features, you’ll improve their reliability, latency, and robustness as they become core product workflows.
• High ownership and senior scope. This is a senior role with real influence on architecture and product direction.

Technical Environment

• Core Languages: Python, SQL
• AI: Dust, LangChain, LangGraph, LangSmith
• Automation: n8n
• Data Warehouse: Snowflake
• Orchestration & Deployment: Dagster, Kubernetes, Docker, Terraform
• Data Ingestion: Fivetran, Airbyte, custom scripts
• Data Sources: PostgreSQL, Elasticsearch, various APIs (Hubspot, Notion, etc.)

About You

• 5+ years of experience in software engineering and a proven track record of shipping production systems.
• Hands‑on experience building LLM‑powered features in production, with a clear understanding of trade‑offs (quality, cost, latency, safety) and how they connect to product and business needs.
• Ability to systematically improve LLM systems: versioned prompts, offline/online evaluations, data analysis, and iteration based on real‑world signals.
• Experience industrializing LLM systems at scale (caching, batching, model routing, observability, rate limiting, ML CI/CD pipelines).
• Strong in Python and comfortable working with REST APIs and making pragmatic architectural decisions.
• Senior‑level engineer: debugging complex systems, refactoring with intent, reviewing code thoughtfully, and anticipating scalability.
• Ownership mentality: identify gaps, propose solutions, and go beyond immediate scope.
• Link technical decisions to product and business outcomes.
• Regular use of AI tools in daily workflow.
• Clear communication and effective collaboration, especially with ML teams.
• Fluent in English (written and spoken) and comfortable in an international environment.

Desirable Skills

• Basic knowledge of Kubernetes and Terraform to independently deploy and operate services.
• French is a plus for day‑to‑day collaboration in our Paris office.

Benefits

• Package that includes BSPCE
• Lunch voucher (Swile, 9€ at 50%)
• Sponsored Wellpass (gymlib)
• Non‑charged health insurance for children (Sidecare / Generali)
• Up to €300 to improve your home office set‑up
• Yearly holiday allowance
• Referral bonus of 4000€ for any new Guardian we might hire thanks to you
• Team building: monthly budget dedicated to each employee to spend with colleagues (e.g., restaurant, karaoke, stand‑up show, kitesurfing week‑end)
• Remote policy: hybrid (3 days/week at the office in Paris)
• Opportunities for career development in the long term