As our Backend Engineer, you are the architect of this system.
You’ll be building the agentic workflows, RAG pipelines, and core infrastructure that turn unstructured global data into a high-speed commerce engine.
🛠 Your Core Focus: Agentic Systems & Scale
- We are looking for a builder who cares deeply about LLM orchestration and system performance.
- Agentic Infrastructure: Design and implement autonomous agents that can research, crawl, and synthesize complex technical specifications without human intervention.
- LLM Engineering: Architect robust RAG pipelines and optimize model performance (latency, cost, and accuracy) to handle massive datasets.
- Product Ownership: Lead the development of a high-performance, AI-native UI. You’ll be responsible for how users interact with complex agent outputs.
- Strategic Decision-Making: As the first technical hire, you will decide the stack, infrastructure (AWS/GCP/Vercel), and AI frameworks (LangChain, LlamaIndex, or custom orchestration) that will scale the company.
- Full-Stack Execution: Bridge the gap between sophisticated backend AI logic and a sleek, reactive frontend using the PERN stack or equivalent modern frameworks.
- 4+ Years of High-Octane Engineering: You’ve been in the trenches, ideally in a VC-backed startup. You know how to ship features in days, not months.
- AI Proficient: You don't just "use" ChatGPT; you understand vector embeddings, prompt chaining, and how to build deterministic guardrails around probabilistic models.
- Technical Toolkit: Expert in JavaScript/TypeScript, deep experience with the PERN stack, and hands-on experience with vector databases (Pinecone, Weaviate, etc.) and LLM APIs.
- Academic Foundation: Degree in Computer Science or Software Engineering—you understand the "why" behind the code (data structures, algorithms, and system design).
- Entrepreneurial Velocity: You thrive in ambiguity. You’d rather build a prototype and break it than sit in a meeting talking about it.
