Expert RAG Engineer

This is a fully remote position, open to applicants in Mexico, +1 more country.

📋 Description

• Design and manage comprehensive RAG architectures from the ingestion of documents to the generation of grounded, cited responses.

• Develop sophisticated retrieval strategies that include hybrid search, reranking, query rewriting/expansion, metadata filtering, and multi-step or agentic retrieval.

• Establish chunking and indexing strategies for both structured and semi-structured data sources, such as XML/XSD, Office formats, PDFs, and scanned documents.

• Choose, benchmark, and refine embedding models.

• Oversee vector databases like pgvector, Qdrant, Weaviate, Milvus, and Azure AI Search at scale.

• Create continuous evaluation frameworks to assess retrieval and generation quality.

• Mitigate hallucinations through grounding, citation, guardrails, and confidence management.

• Implement permission-aware and multi-tenant retrieval systems.

• Develop integrations using the Model Context Protocol (MCP) to connect RAG systems and internal data sources to LLMs and agents.

• Enhance LLM serving with Ollama and llama.cpp, focusing on GGUF quantization, GPU/CUDA tuning, batching, caching, and offline/air-gapped deployments.

• Establish RAG architecture standards, reference implementations, and best practices.

• Review designs and code, providing technical mentorship to AI Developers.

• Convert client and product requirements into effective retrieval strategies that meet quality, latency, and cost objectives.

• Assess emerging techniques such as GraphRAG, long-context trade-offs, and agentic RAG.

• Deploy and scale RAG services on Microsoft Azure and AWS utilizing Docker and Kubernetes.

• Maintain CI/CD pipelines for AI services.

• Implement observability for tracing, retrieval diagnostics, latency, costs, and quality metrics dashboards.

• Support event-driven ingestion and re-indexing pipelines using Apache Kafka.

• Diagnose root causes across the technology stack.

⛳️ Requirements

• 6+ years of experience in backend development, machine learning, or infrastructure.

• 2+ years of experience in building production RAG systems, including end-to-end architecture, hybrid retrieval, reranking, chunking, indexing, and evaluation frameworks.

• Expert-level proficiency in Python programming.

• In-depth knowledge of embeddings, vector databases, and metrics-driven evaluation methodologies.

• Practical experience in serving and optimizing open-source LLMs (Ollama, llama.cpp) with quantization techniques.

• Skilled in GPU/CUDA troubleshooting and performance optimization.

• Strong proficiency in Microsoft Azure, AWS, Docker, Kubernetes, Linux, and CI/CD pipelines (preferably Azure DevOps).

• Familiarity with the Model Context Protocol (MCP).

• Excellent communication skills, along with technical leadership and a strong sense of ownership.

• Capability to collaborate effectively in a distributed, remote work environment.

🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Comprehensive health, dental, and vision insurance plans.

• Flexible working hours and remote work options.

• Opportunities for professional development and continuous learning.

• A dynamic and inclusive work culture that fosters innovation.