Senior AI/LLM Engineer – End-to-End Feature Shipper (Hybrid)

Engg; San Carlos; Híbrido; ARS 274.156.000 - 350.311.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Healthcare coverage

PTO

401(k) plan

Descripción de la vacante

Beacon AI seeks a senior engineer to own LLM feature development end-to-end in a hybrid role based in San Carlos, CA. You will design retrieval and tool-calling flows, build services in Python or TypeScript, and ensure robust, cost-conscious production outputs with strong observability.

You will collaborate with ML/infra and product teams to deploy safe, scalable AI features, maintain data pipelines, and evaluate latency, accuracy, and reliability in a safety-critical aviation context.

Formación

• 5-8 years of experience in ML/LLM systems, production experience preferred.
• Ability to ship end-to-end features with clear contracts and observability.
• Strong understanding of retrieval-augmented generation and tool-calling.

Responsabilidades

• Design and implement LLM features end-to-end (retrieval, tool-calling, prompts).
• Deliver robust JSON and schema-bound outputs with validation, retries, and fallbacks.
• Own the service layer with Python/TypeScript APIs and workers, including monitoring.

Conocimientos

LLM features

RAG

Tool-calling

Cost awareness

Educación

Bachelor’s or higher in CS/ML

Herramientas

Python

TypeScript

APIs

Descripción del empleo

Beacon AI seeks a senior engineer to own LLM feature development end-to-end in a hybrid role based in San Carlos, CA. You will design retrieval and tool-calling flows, build services in Python or TypeScript, and ensure robust, cost-conscious production outputs with strong observability.

You will collaborate with ML/infra and product teams to deploy safe, scalable AI features, maintain data pipelines, and evaluate latency, accuracy, and reliability in a safety-critical aviation context.