Remote Agentic AI Engineer: RAG Architect for LLM Systems

AspenView Technology Partners; Bogotá; Híbrido; COP 381.667.000 - 572.501.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Competitive base

Benefits & wellness

Flexible work model

Growth opportunities

Inclusive culture

Descripción de la vacante

AspenView Technology Partners seeks a senior AI engineer to architect autonomous agentic workflows, design robust RAG pipelines, and evaluate LLMs for healthcare tasks. You will optimize vector databases, implement safety guardrails, and collaborate with US researchers and product teams to deliver compliant, scalable AI solutions.

Join a nearshore, remote-first team that values robust engineering, strong communication, and nearshore collaboration with US clients.

Formación

• 4+ years in software production engineering, with at least 2+ years dedicated to building LLM applications, agentic workflows, and RAG architectures in production.

Responsabilidades

• Architect and deploy autonomous agentic AI workflows and multi-agent systems.
• Design, optimize, and scale production RAG pipelines with hybrid search, re-ranking, and context handling.
• LLM fine-tuning and evaluation for healthcare tasks, establishing rigorous evaluation frameworks.
• Manage vector stores for high-concurrency, low-latency similarity searches.
• Implement enterprise safety controls and HIPAA compliance guardrails.
• Collaborate with US clinical researchers, cloud architects, and product leads.

Conocimientos

Agentic frameworks

LangGraph

LlamaIndex

AutoGen

CrewAI

Python

LLM orchestration

Vector databases

Pinecone

Qdrant

Milvus

Weaviate

pgvector

TruLens

Herramientas

Pinecone

Qdrant

Milvus

Weaviate

pgvector

TruLens

Descripción del empleo

AspenView Technology Partners seeks a senior AI engineer to architect autonomous agentic workflows, design robust RAG pipelines, and evaluate LLMs for healthcare tasks. You will optimize vector databases, implement safety guardrails, and collaborate with US researchers and product teams to deliver compliant, scalable AI solutions.

Join a nearshore, remote-first team that values robust engineering, strong communication, and nearshore collaboration with US clients.