Context & Memory Engineer - Q126

Job Title: Context & Memory Engineer

Company: R2 Technologies

Location: Alpharetta, GA (Hybrid / Remote Options Available)

Employment Type: Full-Time / Contractual

About R2 Technologies: R2 Technologies is a Certified Minority Business Enterprise (MBE) headquartered in Alpharetta, GA. With over two decades of experience across global markets, we have built a reputation as a trusted partner for IT staffing excellence and cutting-edge digital product innovation. We are driven by innovation and operate on a simple philosophy: "We deliver what we promise, and we promise only what we can deliver." Beyond providing top-tier IT talent, R2 builds cutting-edge proprietary solutions like SmartEnt—an Enterprise AI & IoT Intelligence Platform utilizing advanced NLP and AI technologies. By partnering closely with our clients, we deliver technology-driven outcomes that are realistic, measurable, and impactful.

Job Summary: An AI's output is only as good as the context it is grounded in. R2 Technologies is looking for a Context & Memory Engineer to build the connective tissue between our enterprise data and advanced language models. You will be responsible for ensuring our autonomous systems maintain persistent state, conversational continuity, and semantic understanding without compromising data security or speed.

Key Responsibilities: * Architect and maintain advanced Retrieval-Augmented Generation (RAG) pipelines that feed highly relevant, real-time enterprise context to foundation models.

Implement and manage stateful memory architectures for LLM agents using the Model Context Protocol (MCP) and long-term storage mechanisms.

Deploy, optimize, and tune Vector Databases (e.g., Pinecone, Qdrant, Milvus) and Graph Databases (e.g., Neo4j) to map complex semantic relationships and entity graphs.

Develop chunking, embedding, and re-ranking strategies to maximize the accuracy and relevance of context retrieved for the AI models.

Monitor token limits and optimize context window utilization to balance latency, cost, and reasoning quality.

Actively utilize AI-assisted development tools to accelerate the construction of data ingestion and semantic mapping pipelines.

Qualifications: * Up to 3 years of experience in Data Engineering, AI/ML Engineering, or Backend Development.

Strong proficiency in Python and familiarity with data orchestration pipelines.

Hands-on experience building RAG systems and working with frameworks like LlamaIndex or LangChain.

Experience deploying and querying Vector Databases and/or Knowledge Graphs.

Proven experience or strong familiarity working alongside AI coding assistants to enhance productivity.

Understanding of embedding models, semantic search techniques, and the nuances of LLM context windows (e.g., Claude's 200k+ context capabilities).