AI Engineer (Trust & Explainability, AI Platform)

Join MeridianLink as an AI Engineer focused on Trust & Explainability. In this deeply technical, hands-on role, you will work on tracing agent actions across a multi-agent workflow, adopting and extending leading open-source explainability and observability frameworks. You will build the primitives that product teams use to surface explanations to lenders, credit unions, and their borrowers. This is an opportunity to build expertise in AI while working alongside a supportive team of engineers and architects.

• Écrire le code qui trace les actions des agents à travers un flux de travail multi-agent, en adoptant et en étendant les frameworks d'explicabilité et d'observabilité open-source.
• Comprendre comment instrumenter un agent afin qu'une seule conversation puisse être suivie depuis le premier message de l'utilisateur jusqu'à la réponse finale.
• Collaborer avec les ingénieurs produits pour déterminer ce qu'un agent doit divulguer à la surface du produit : ce qu'il a fait, quelles données il a utilisées, à quel point il était confiant.

• Bachelor's degree in Computer Science, Software Engineering, or equivalent experience
• 3+ years of professional software engineering experience, delivering features independently in a production environment
• Experience with distributed tracing or observability tooling in a production system
• Proficiency in Python with production experience; TypeScript a plus
• Proficiency with standard development tooling: Git, Docker, automated testing, and modern scripting languages
• Hands-on experience building software that integrates large language models (LLM APIs, agent frameworks, RAG pipelines, or similar), in production or in substantial personal or open-source projects
• Solid understanding of algorithms, data structures, and software design fundamentals
• Hands-on experience in at least one of the following, with real interest in growing into the others: LLM observability and tracing, LLM evaluation and testing, agent frameworks and multi-agent orchestration, or application security testing
• Strong automated testing instincts, including an interest in how to test systems that do not return the same answer twice
• Experience running workloads on Azure or AWS, including the basics of identity and access management, networking, and secrets management
• Active daily use of AI-assisted development tools
• Experience with OpenTelemetry, including the GenAI semantic conventions, or OpenLLMetry
• Experience with LLM observability and evaluation tools (Langfuse, Arize Phoenix, LangSmith, Braintrust, promptfoo, DeepEval, or equivalent)
• Contributions to open-source AI observability, evaluation, or agent framework projects
• Experience with cloud-managed model services such as AWS Bedrock or Azure OpenAI
• Experience building or operating multi-tenant SaaS systems where tenant isolation was a hard requirement
• Prior experience in financial services, fintech, or another regulated industry where explainability shaped technical decisions
• Experience building developer-facing debugging or visualization tools