You’ll be a core builder of Atrix’s backend infrastructure, powering AI-native workflows that ingest unstructured data, structure it with AI, and deliver insights that matter—instantly and reliably.
You’ll work on scalable data pipelines, robust APIs, and real-time inference systems, supporting everything from complex agent workflows to customer-facing dashboards. Whether it’s building retrieval pipelines, optimizing async background workers, or designing clean, secure APIs, your work will be foundational to how our platform works and scales.
We’re building a modular, agentic platform that connects to customer-approved data sources, transforms unstructured data using LLM-based agents, and delivers decision-ready intelligence to regulated teams.
You’ll tackle rich backend engineering challenges like:
•
⚙️ System Design & Reliability – Scale to handle massive amounts of records with fast response times
•
🧠 LLM Ops – Make AI outputs explainable, auditable, and efficient
•
🛠 Multi-Tenant Infra – Isolate customer data across parallelized pipelines
•
🚀 AI Performance Tuning – Optimize inference cost, caching, and latency
•
📡 RAG Pipelines & Contextual Workflows – Connect structured + unstructured data for real-world usage
You’ll work closely with the Engineering Lead and CEO, and collaborate across product, AI, and GTM. As one of our earliest backend engineers, you’ll influence everything from our architecture to hiring bar.
💡 This is an in-person role based in NYC, with flexibility for remote work on some days as needed.