Staff AI/LLM Engineer: End-to-End Retrieval & Tooling

Engg; San Carlos; Híbrido; ARS 228.464.000 - 319.849.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Healthcare coverage

PTO 3 weeks

Company holidays

Descripción de la vacante

Beacon AI is building an AI platform for aviation, hiring senior engineers to own cross-team systems. You will ship LLM-powered features end-to-end, focusing on retrieval, tool-calling, and cost-aware design. Expect collaboration with ML, infra, product, and security teams, and to set technical direction across services.

This hybrid role is based in the San Carlos area, with 3+ onsite days and remote work days. You’ll handle high-stakes data with strong emphasis on reliability and safety.

Formación

• Shipped LLM apps with features exposed to users and improved them with data.
• Comfortable writing production code, tests, and docs; keep things simple and observable.
• Deep understanding of embeddings, chunking, vector search tradeoffs, and function calling.

Responsabilidades

• Build user-facing LLM features - Design and implement retrieval-augmented generation and tool-calling flows using frameworks like LangChain or equivalent primitives, where simpler is better.
• Deliver robust JSON and 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, request shaping, prompt templates, and context packing to control latency and cost.
• Integrate with AWS Bedrock, OpenAI, Anthropic, or self-hosted endpoints as needed.
• Retrieval and data prep - Collaborate with infrastructure teammates to develop chunking, embeddings, and indexing capabilities for documents, time series, and multimedia.
• Choose and tune vector backends such as OpenSearch, pgvector, or Pinecone.
• Keep knowledge bases fresh with data syncs from S3, Aurora, DynamoDB, and external sources.
• Evaluation and quality - Create offline evals and golden sets for prompts, retrievers, and tools.
• Stand up online metrics for task success, hallucination rate, retrieval precision/recall, p95 latency, and cost per request.
• Run A/B tests and prompt/version rollouts with guardrails and canaries.
• Safety, privacy, and compliance - Implement content and policy checks, PII detection and redaction, access controls, and auditing.
• Design human-in-the-loop paths for sensitive actions.
• Handle aviation data with care and follow internal security standards.
• Operate what you build - Add tracing, logs, and dashboards for model calls, token usage, errors, and saturation.
• Debug tricky failures across retrieval, prompts, tools, and providers.

Conocimientos

LLM feature development

Python/TypeScript

RAG and tool-calling

Performance observability

Systems ownership

Herramientas

LangChain

AWS Bedrock

OpenAI

Anthropic

Self-hosted endpoints

Descripción del empleo

Beacon AI is building an AI platform for aviation, hiring senior engineers to own cross-team systems. You will ship LLM-powered features end-to-end, focusing on retrieval, tool-calling, and cost-aware design. Expect collaboration with ML, infra, product, and security teams, and to set technical direction across services.

This hybrid role is based in the San Carlos area, with 3+ onsite days and remote work days. You’ll handle high-stakes data with strong emphasis on reliability and safety.