Aviation LLM Engineer – End-to-End AI Features

Engg; San Carlos; Híbrido; ARS 274.156.000 - 396.003.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Healthcare 100% coverage for employees

3 weeks PTO + 13+ holidays

401(k) plan

Descripción de la vacante

Beacon AI in the United States is hiring senior engineers to build LLM-powered features end-to-end for aviation safety. You’ll design retrieval-augmented generation, implement tool-calling, and ship robust services in Python or TypeScript with strong contracts and observability.

The role emphasizes cost, latency, and quality, with access to AWS Bedrock, OpenAI, and self-hosted endpoints, plus a focus on safety, privacy, and compliance.

Formación

• Shipped LLM apps and features in production.
• Strong builder with production code, tests, and docs.
• Knowledge of embeddings, chunking, and vector search.

Responsabilidades

• Build user-facing LLM features with retrieval-augmented generation and tool-calling flows.
• Deliver robust JSON/schema-bound outputs with validation, retries, and fallbacks.
• Add function calling to integrate with internal tools, search, routing, and data services.
• Own the service layer—ship APIs and workers in Python or TypeScript with clear contracts, streaming, and backoff.
• Add caching, prompt templates, and context packing to control latency and cost.
• Integrate with Bedrock/OpenAI/Anthropic or self-hosted endpoints as needed.
• Keep knowledge bases fresh with data syncs from S3/Aurora/DynamoDB and external sources.
• Stand up online metrics for task success, hallucination rate, latency, and cost per request.
• Run A/B tests and prompt/version rollouts with guardrails and canaries.
• Design human-in-the-loop paths for sensitive actions.
• Operate with tracing, logs, and dashboards for model calls and errors.

Conocimientos

LLM features

Production code

Observability

RAG and tools

Cost and latency

Herramientas

Python

TypeScript

LangChain

AWS Bedrock

OpenAI

Anthropic

OpenSearch

pgvector

Pinecone

Weaviate

Descripción del empleo

Beacon AI in the United States is hiring senior engineers to build LLM-powered features end-to-end for aviation safety. You’ll design retrieval-augmented generation, implement tool-calling, and ship robust services in Python or TypeScript with strong contracts and observability.

The role emphasizes cost, latency, and quality, with access to AWS Bedrock, OpenAI, and self-hosted endpoints, plus a focus on safety, privacy, and compliance.