Job Description
This role involves architecting, implementing, and optimizing backend systems supporting AI agent interactions, including ingestion, indexing, retrieval, embedding/memory management, tool‑call orchestration, context tracking, and ranking. You will build scalable pipelines and services to support real‑time, multimodal interactions with tight latency and throughput constraints. Design APIs, data models, caching and indexing layers, retrieval/feedback loops, context‑management frameworks, and tool‑call workflows are critical.
You will integrate retrieval‑augmented generation (RAG), hybrid search/ranking, vector/embedding lifecycle management, and memory systems into production services. Defining and monitoring metrics for latency, throughput, freshness, memory/context state size, retrieval relevance, tool‑call success, and system health is a key responsibility. Collaboration with ML/IR, product, and frontend teams is essential for delivering end‑to‑end capabilities, shaping how Superhumans reason and act. You will also mentor engineers, lead design/code reviews, set engineering best practices, and influence technical vision and architecture.
About 1mind
1mind is a platform that deploys multimodal Superhumans for revenue teams, combining a face, a voice, and a GTM brain equipped with deep technical and product knowledge.