Назад
Company hidden
6 дней назад

AI Engineer – Trust & Explainability (AI Platform)

104 148 - 177 600$
Формат работы
remote (только USA)
Тип работы
fulltime
Грейд
middle
Английский
b2
Страна
US
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
AI Engineer – Trust & Explainability (AI Platform) (AI): Building shared runtime services for AI agents, including multi-agent tracing, evaluation, explainability, and safety controls with an accent on LLM observability, tenant isolation, and regulated lending workflows. Focus on designing readable traces, customer-facing explanation primitives, adversarial testing, and automated quality checks for model and prompt changes.

Location: US Remote

Salary: $104,148–$177,600 per year

Company

hirify.global builds the hirify.global One platform for credit unions and lenders, including shared AI agent infrastructure and financial technology products.

What you will do

  • Build tracing across model calls, tool calls, retrieval, memory, handoffs, parallel branches, and retries in multi-agent workflows.
  • Develop readable developer-facing traces and customer-facing explanation records, including confidence and provenance metadata.
  • Evaluate, integrate, and extend open-source LLM observability, tracing, and evaluation frameworks.
  • Build evaluation tooling for golden datasets, scoring pipelines, regression reporting, and model or prompt comparisons.
  • Create red-team and adversarial tests for prompt injection, jailbreaks, tool misuse, data exfiltration, and tenant-isolation failures.
  • Collaborate with product engineers, Security Operations, architects, and AI engineering teammates through design reviews, code reviews, and documentation.

Requirements

  • 3+ years of professional software engineering experience delivering production features independently.
  • Production proficiency in Python; TypeScript experience is a plus.
  • Hands-on experience building software with LLM APIs, agent frameworks, RAG pipelines, or similar systems.
  • Experience with distributed tracing or observability tooling, automated testing, and at least one of LLM observability, LLM evaluation, multi-agent orchestration, or application security testing.
  • Experience with Git, Docker, automated testing, modern scripting languages, and workloads on Azure or AWS, including identity, networking, and secrets management.
  • Bachelor’s degree in Computer Science, Software Engineering, or equivalent experience; daily use of AI-assisted development tools.

Nice to have

  • Experience with OpenTelemetry, GenAI semantic conventions, OpenLLMetry, Langfuse, Arize Phoenix, LangSmith, Braintrust, promptfoo, DeepEval, or equivalent tools.
  • Open-source contributions to AI observability, evaluation, or agent framework projects.
  • Experience with AWS Bedrock, Azure OpenAI, multi-tenant SaaS, or regulated financial services.
  • Experience building developer-facing debugging or visualization tools.

Culture & Benefits

  • Remote work in a full-time role.
  • Medical, dental, vision, life, and disability insurance coverage.
  • Flexible paid time off and paid holidays.
  • 401(k) plan with company match.
  • Background, credit, and drug checks are part of the offer process.

Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →