AI Engineer – Trust & Explainability (AI Platform)
MeridianLink15 hours ago
Remote, United StatesMid Level
H1B sponsor
Base Salary
$104k - $178k/yr
Responsibilities
- Build end-to-end tracing and correlation for multi-agent workflows across gateway, orchestration, memory, retrieval, tools, handoffs, parallel branches, and retries.
- Create developer-facing trace views and human-readable explanations of agent actions, data sources, decisions, and confidence.
- Build customer-facing explanation, provenance, and confidence primitives and partner with product engineers to integrate them into real products.
- Evaluate, integrate, extend, and where appropriate contribute to open-source LLM observability, tracing, and evaluation frameworks.
- Build evaluation tooling including golden dataset management, test runners, scoring pipelines, regression reporting, and model or prompt comparisons.
- Create red-team and adversarial test suites for prompt injection, jailbreaks, tool misuse, data exfiltration, and cross-tenant data access.
- Collaborate with Security Operations on threat models, participate in design reviews and code reviews, support L1 teammates, and improve documentation.
Requirements
- At least 3 years of professional software engineering experience delivering production features independently.
- Strong understanding of algorithms, data structures, and software design fundamentals.
- Proficiency with Git, Docker, automated testing, and modern scripting languages.
- Daily active use of AI-assisted development tools.
- Bachelor’s degree in Computer Science, Software Engineering, or equivalent experience.
- Hands-on experience building production or substantial personal/open-source software integrating LLM APIs, agent frameworks, RAG pipelines, or similar systems.
- Production Python proficiency; TypeScript is a plus.
- Hands-on experience in LLM observability and tracing, LLM evaluation and testing, agent frameworks and multi-agent orchestration, or application security testing, with interest in developing the other areas.
- Production experience with distributed tracing or observability tooling and strong automated testing practices for nondeterministic systems.
- Experience running workloads on Azure or AWS, including identity and access management, networking, and secrets management.
- Preferred experience with OpenTelemetry and GenAI semantic conventions, OpenLLMetry, LLM observability or evaluation tools, open-source AI projects, AWS Bedrock, Azure OpenAI, multi-tenant SaaS isolation, regulated industries, or developer-facing debugging and visualization tools.
Categories
About MeridianLink
MeridianLink builds cloud software for financial institutions to open accounts, originate consumer and mortgage loans, manage collections, and verify data. Its platform is sold to banks, credit unions, and consumer reporting agencies via subscriptions with implementation and managed services. Founded in 1998 and headquartered in Irvine, CA, MeridianLink is a public company on the NYSE.