3 months ago
Remote, ColombiaSenior
Responsibilities
- Build low-latency API layers, production-grade RAG systems, complex ingestion pipelines, and Human-in-the-Loop workflows.
- Collaborate with Data Engineers to convert raw data lakes and streams into production-ready AI feature prototypes.
- Design GraphQL and REST integrations, including token-aware pagination and enterprise ingestion systems.
- Implement vector retrieval, embedding generation, secure LLM validation, Bedrock agents and guardrails, and durable HITL workflows.
- Develop stateful orchestration, idempotent processing, rollback and dead-letter handling, and end-to-end event tracing.
Requirements
- 7+ years of overall experience in backend software engineering and AI application engineering, including exposure to distributed systems.
- 2+ years of experience engineering production-grade RAG pipelines, managing vector retrieval context, and implementing secure LLM validation layers.
- Proven ability to collaborate synchronously with Data Engineers to turn data lakes and streams into production AI feature prototypes.
- Proficiency in advanced API design, GraphQL architecture, RAG, data flows, ingestion pipelines, state management, and Human-in-the-Loop automation.
- Production fluency in Python.
- Working knowledge of C# with .NET Core, Java, or Node.js with TypeScript for enterprise ingestion systems.
- Preferred experience includes Apollo Server, AWS AppSync, Amazon Bedrock, Knowledge Bases for Amazon Bedrock, OpenSearch, Elasticsearch, pgvector, MemoryDB, Redis OSS, Amazon SQS, MSK, Kafka, Pendo, Hotjar, Google Analytics, AWS Step Functions, LangGraph, OpenTelemetry, and Datadog.
Benefits
- Fully remote work from Colombia.
- 13 floating holidays.
- 15 vacation days per completed year.
- Good working environment.
Tech Stack
Categories
