AI Engineer – Trust & Explainability (AI Platform) - MeridianLink

About the Role

The AI Platform team is building the shared runtime that powers every AI agent at MeridianLink. We are looking for an AI Engineer to build the trust and explainability layer of that runtime. You will develop the tracing, evaluation, and explanation capabilities that allow engineers to understand multi-agent workflows and enable product teams to provide transparent, trustworthy outputs to our customers.

This is a deeply technical, hands-on role where you will write code to trace agent actions, extend open-source observability frameworks, and build primitives for customer-facing explanations.

Key Responsibilities

Multi-Agent Tracing & Explainability

• Build tracing across the platform's gateway, orchestration, memory, and tool layers.
• Create correlations that link actions across agents in complex, multi-agent workflows.
• Develop developer-facing trace views to make agent conversations readable and debuggable.
• Build the explanation layer that translates raw trace data into human-readable accounts of agent decision-making.

Customer-Facing Trust

• Build platform primitives for explanation records, confidence metadata, and provenance summaries.
• Partner with product engineers to integrate these primitives into real-world lending products.
• Iterate on explanation formats based on feedback from product teams and end-users.

Trust & Explainability Frameworks

• Evaluate and integrate open-source observability, tracing, and evaluation frameworks (e.g., OpenTelemetry, Langfuse, Arize Phoenix).
• Extend existing frameworks and contribute fixes back to the open-source community.

Evaluation Tooling

• Maintain the platform's evaluation framework, including golden dataset management, test runners, and scoring pipelines.
• Run model and prompt comparisons to ensure quality before releases.

Safety & Isolation Testing

• Build red-team and adversarial test suites to defend against prompt injection, jailbreaks, and data exfiltration.
• Implement automated tests to ensure strict tenant isolation across the shared runtime.

Qualifications

• 3+ years of professional software engineering experience.
• Proficiency in Python; TypeScript is a plus.
• Hands-on experience building software that integrates LLMs (LLM APIs, agent frameworks, RAG pipelines).
• Experience with distributed tracing or observability tooling in production.
• Strong automated testing instincts, particularly for non-deterministic systems.
• Experience running workloads on Azure or AWS (IAM, networking, secrets management).
• Active daily use of AI-assisted development tools.
• Bachelor's degree in Computer Science, Software Engineering, or equivalent experience.