6 дней назад
AI Engineer (LLM)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
AI Engineer (LLM): Building and operating LLM-powered features, agentic workflows, and NLP pipelines for insurance claims with an accent on trustworthy evaluation, deterministic workflow execution, privacy, and auditability. Focus on designing event-driven services, tracing model calls, handling retries and partial failures, and protecting regulated personal and medical data.
Location: Chicago (Green St), Illinois, United States
Company
provides a cloud platform and AI-powered technology for the insurance, vehicle repair, automotive, and related industries.
What you will do
- Build and ship LLM-powered features and agentic workflows in Python and TypeScript from product definition through production operations.
- Design evals, guardrails, feedback loops, token budgets, and latency controls for reliable AI features.
- Maintain NLP pipelines that combine semantic search, classical NLP, structured outputs, tool calling, embeddings, and LLMs.
- Build durable event-driven services with retries, idempotent handlers, checkpointed model outputs, and deterministic workflows.
- Trace model calls and agent steps, connect tracing to alerts, and provide citations and auditability for recommendations.
- Model claims data across relational, document, and graph stores while participating in code reviews, technical design, and on-call support.
Requirements
- 3+ years of professional software engineering experience, including an LLM-powered feature operated in production.
- Strong Python and TypeScript skills, including typed, tested, and asynchronous code.
- Experience designing LLM evals and shipping guardrails, as well as reviewing AI-generated code for correctness, security, and design quality.
- Experience with message- or event-driven architectures, long-running workflows, retries, idempotency, event-sourced state, and durable workflow engines such as Temporal or Durable Task Scheduler.
- Experience with relational and non-relational data stores, tenant isolation, regulated personal data, and backend services on Azure or AWS.
- Ability to write technical design documents, communicate with technical and non-technical audiences, and participate in code review.
Nice to have
- React and TypeScript experience for full-stack AI features, including chat, streaming, and citation-heavy interfaces.
- CI/CD and infrastructure as code with Terraform or Bicep.
- Agent frameworks and protocols such as LangGraph, Microsoft Agent Framework, MCP, and A2A.
- LLM observability and evaluation tooling such as LangSmith, Arize, Braintrust, and OpenTelemetry-based tracing.
- Experience with AI A/B testing, historical claims simulations, or insurance, claims, and automotive repair domains.
Culture & Benefits
- Full-time position with an on-call rotation for built services.
- 401(k) matching, paid time off, comprehensive health insurance, and an annual performance bonus.
- Adoption assistance, tuition reimbursement, wellness programs, stock purchase plan options, and employee resource groups.
- Work environment centered on integrity, customer focus, innovation, inclusion and diversity, tenacity, and collaboration.
Hiring process
- A video interview is required and will be transcribed and retained for review.
- Generative AI or automated assistance is not permitted during interviews unless explicitly allowed for a specific exercise.
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 →