AI Engineer – Trust & Explainability (AI Platform)

New

JobgetherAI platform

Fully remote work within the United States.Full-TimeMiddle

Salary104,148 - 177,600 USD per year

Apply NowOpens the employer's application page

Job Details

Have 3+ years of professional software engineering experience delivering production features independently.
Hold a bachelor's degree in Computer Science, Software Engineering, or a related field, or have equivalent practical experience.
Have strong foundations in algorithms, data structures, software design, and modern engineering practices.
Have production-level proficiency with Python; TypeScript experience is a plus.
Have hands-on experience building applications integrating LLMs, such as LLM APIs, agent frameworks, or RAG pipelines.
Use AI-assisted software development tools daily.
Have experience with Git, Docker, automated testing, and modern scripting or development tooling.
Have 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.
Have production experience with distributed tracing or observability tooling and strong automated testing practices for variable outputs.
Have experience running workloads on AWS or Azure, including foundational knowledge of identity and access management, networking, and secrets management.
Preferred: experience with OpenTelemetry, GenAI semantic conventions, OpenLLMetry, or comparable tracing standards.
Preferred: familiarity with LLM observability and evaluation platforms such as Langfuse, Arize Phoenix, LangSmith, Braintrust, promptfoo, or DeepEval.

Build end-to-end tracing across AI platform components, including orchestration, memory, tools, model calls, agent handoffs, parallel branches, and retries.
Develop correlation capabilities and developer-facing debugging experiences for complete multi-agent workflows.
Create human-readable explanations of agent actions, information used, and decision paths.
Build customer-facing trust primitives, including explanation records and confidence and provenance metadata.
Integrate trust and explainability capabilities into production AI applications with product engineering teams.
Evaluate and extend open-source observability, tracing, and evaluation frameworks.
Develop evaluation tooling, versioned datasets, and automated quality checks for model, prompt, and tool changes.
Build adversarial, red-team, and tenant-isolation tests, and work with Security Operations on threat models and attack patterns.
Participate in design discussions and code reviews, support junior AI engineers, and contribute documentation.

View Full Description & ApplyYou'll be redirected to the employer's site