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

At KR Elixir Inc., a pioneering technology company based in Santiago, Chile, we're on a mission to revolutionize AI-driven solutions. Join our dynamic team as an AI Engineer or Senior AI Engineer specializing in Agentic Systems and Large Language Model (LLM) Integration. This full-time hybrid role offers a unique opportunity to work at the forefront of AI innovation, designing and deploying production-grade multi-agent architectures and retrieval-augmented generation (RAG) pipelines that power next-generation applications. As part of KR Elixir, you will engage in impactful projects that shape AI safety and reliability in real-world customer environments. We value career development and provide advancement opportunities within a collaborative, growth-oriented culture. Located in vibrant Santiago, this position blends remote flexibility with on-site collaboration, ensuring a balanced work-life experience. Key Responsibilities Design and implement robust multi-agent architectures with persistent conversation and session state management to ensure seamless user interactions. Develop and operate advanced RAG pipelines, including vector search and reranking techniques, to minimize hallucinations and enhance response accuracy. Integrate function and tool-calling capabilities using API bindings and JSON schema outputs, enabling dynamic execution and feedback loops within LLMs. Create comprehensive evaluation frameworks such as LLM-as-a-Judge workflows, golden datasets, and rubrics for automated and scalable model output grading. Manage conversation history and context window strategies to support multi-turn dialogue coherence and session retrieval in production environments. Collaborate with engineering and infrastructure teams to integrate LLMs, vector databases, and Postgres databases, ensuring high availability and telemetry monitoring. Produce clear technical designs, runbooks, and unit/integration tests to enable reproducible failures and component-level observability. Partner closely with product managers, data scientists, and QA teams to deploy, A/B test, and tune performance for continuous improvement. What We're Looking For Required: Proven experience building production LLM or agent-based applications, especially with RAG systems. Strong hands-on expertise with agent frameworks, persistence layers, and session state management. Proficiency in vector search technologies, cross-encoder reranking, and context hygiene methods. Experience integrating APIs and function/tool-calling mechanisms with LLMs. Solid background in designing evaluation and testing frameworks for AI models. Familiarity with databases such as Postgres and vector DBs, plus telemetry and monitoring tools. Excellent collaboration and communication skills within cross-functional teams. Bachelor’s degree or higher in Computer Science, Engineering, or related field; advanced degrees preferred. Preferred: Experience with multi-agent runtime environments and checkpointing mechanisms. Knowledge of AI safety, reliability, and ethical considerations in LLM deployment. Familiarity with cloud infrastructure and container orchestration. Passion for continuous learning and professional growth in AI technologies. What We Offer Competitive compensation aligned with Chile’s tech market standards. Health insurance coverage to support your well-being. Paid time off to maintain a healthy work-life balance. Retirement plan options for your future security. Hybrid work environment combining remote flexibility with in-office collaboration. Professional development opportunities including workshops, conferences, and certifications. Innovative projects that challenge and expand your AI expertise. Supportive team culture focused on growth, diversity, and inclusion. Frequently Asked Questions What is the primary focus of this AI Engineer role? The role centers on designing and operating multi-agent AI systems and integrating large language models with production-grade reliability and s