AI Engineer – Trust & Explainability (AI Platform)

The role

This role builds the trust and explainability layer of the MeridianLink One AI platform runtime. You will develop tracing, evaluation, and explanation capabilities to help engineers and product teams understand multi-agent workflows.

What you will do

• Build tracing across the platform's gateway, orchestration, memory, and tool layers
• Build correlation that links actions across agents in a single multi-agent workflow
• Build developer-facing trace views and human-readable explanation layers
• Build platform primitives for end users like explanation records and confidence metadata
• Evaluate and integrate open-source observability, tracing, and evaluation frameworks
• Build and maintain components of the platform's evaluation framework
• Build red-team and adversarial test suites for prompt injection and jailbreak attempts
• Build automated test suites to prove tenant isolation
• Participate in design discussions and code reviews
• Support onboarding of L1 AI Engineer teammates

Required qualifications

• 3+ years of professional software engineering experience delivering features independently in a production environment
• Solid understanding of algorithms, data structures, and software design fundamentals
• Proficiency with Git, Docker, automated testing, and modern scripting languages
• Active daily use of AI-assisted development tools
• Bachelor's degree in Computer Science, Software Engineering, or equivalent experience
• Hands-on experience building software that integrates large language models (LLM APIs, agent frameworks, RAG pipelines, or similar) in production or substantial personal or open-source projects
• Proficiency in Python with production experience
• Hands-on experience in at least one of: LLM observability and tracing, LLM evaluation and testing, agent frameworks and multi-agent orchestration, or application security testing
• Experience with distributed tracing or observability tooling in a production system
• Strong automated testing instincts
• Experience running workloads on Azure or AWS, including identity and access management, networking, and secrets management

Nice to have

• 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
• Experience building developer-facing debugging or visualization tools
• TypeScript

About the company

MeridianLink is building the MeridianLink One platform, which includes a shared runtime for AI agents used by credit unions and lenders.