Senior LLM Engineer - AI Apps & Tooling

Beacon AI; San Carlos; Híbrido; ARS 228.464.000 - 319.849.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Healthcare coverage

Paid time off

401(k)

Descripción de la vacante

Beacon AI in San Carlos, CA is seeking a senior ML/LLM engineer to own features end-to-end, from retrieval-augmented generation to tool-calling and production deployment.

You will collaborate with ML/infra and product teams to design scalable, low-latency, and cost-aware solutions in a safety-critical aviation domain. The role is hybrid with onsite and remote work options within the US.

Formación

• 5-8 years experience in ML/LLM, production ML/LLM systems preferred.
• Ability to own features end-to-end from design to production.
• Strong emphasis on evaluation, guardrails, and cost/latency controls.

Responsabilidades

• Build user-facing LLM features with robust outputs and schema validation.
• Own the service layer: APIs, workers, and contracts in Python or TypeScript.
• Handle retrieval, embeddings, and indexing for documents and time series.
• Create offline evals and online metrics for task success and latency.
• Implement safety, privacy, and compliance measures across systems.
• Operate and monitor the deployed services with tracing and dashboards.

Conocimientos

LLM development

RAG systems

Tool-calling

Python

TypeScript

ML evals

Latency optimization

Herramientas

LangChain

OpenAI

Bedrock

Anthropic

OpenSearch

Pinecone

Descripción del empleo

Beacon AI in San Carlos, CA is seeking a senior ML/LLM engineer to own features end-to-end, from retrieval-augmented generation to tool-calling and production deployment.

You will collaborate with ML/infra and product teams to design scalable, low-latency, and cost-aware solutions in a safety-critical aviation domain. The role is hybrid with onsite and remote work options within the US.