AI Engineer / Senior AI Engineer - Agentic Systems & LLM Integration in Santiago, Chile

Role: AI Engineer / Senior AI Engineer (Agentic Systems & LLM Integration)

Location: Santiago, Chile

Employment Type: Full Time (Hybrid)

Role Summary

KR Elixir Inc. is seeking an experienced AI Engineer to design, build, and operate production-grade agentic AI systems and large language model (LLM) integrations. This role is responsible for the technical implementation of multi-agent architectures, retrieval-augmented generation (RAG) pipelines, tool and function calling, evaluation frameworks, and session/state management to ensure LLM-based applications perform reliably and safely in customer environments.

Key Responsibilities

• Design and implement multi-agent architectures and runtime components that persist conversation/session state (e.g., checkpointers and persistence layers).
• Build and operate RAG pipelines, including vector search, reranking (cross-encoder or equivalent), and context hygiene to minimize hallucinations.
• Implement function and tool-calling integrations, including API/function binding, JSON schema outputs, and runtimes that execute and feed results back to LLMs.
• Create evaluation and testing frameworks such as LLM-as-a-Judge workflows, golden datasets, and rubrics for automated grading of model outputs.
• Design and manage conversation history and context window strategies to ensure multi-turn references resolve correctly.
• Collaborate with engineering and infrastructure teams to integrate LLMs, vector databases, Postgres databases, and monitoring/telemetry for production resilience.
• Produce clear technical designs, runbooks, and unit/integration tests for agent components; enable reproducible failures and component-level observability.
• Work closely with product, data science, and QA teams on deployment, A/B testing, and performance tuning.

Required Skills & Experience

• Proven experience building production LLM/agent applications or retrieval-augmented generation (RAG) systems.
• Hands-on experience with agent frameworks and persistence concepts.