The company is looking for a software engineer to build scalable, production-grade applications that leverage AI models like GPT-4, Claude, or open-source LLMs, moving beyond simple prompt templating to create AI-powered solutions.
Requirements
- Have strong backend skills (Python, Node, Go, PHP.) and can write clean, production-grade code
- Have shipped something real using OpenAI, Anthropic, or similar APIs
- Understand prompt engineering beyond surface-level hacks
- Know your way around APIs, databases, cloud infra, and testing frameworks
- Experience with full-stack frameworks (React, Svelte, etc.)
- Experience with fine-tuning or using open-source models (e.g. Mistral, LLaMA, Zephyr)
- Familiarity with n8n, LangChain, or retrieval-augmented generation pipelines
Responsibilities
- Building internal tools, APIs, and full-stack apps where LLMs are a core part of the logic
- Integrating models like GPT-4 into real workflows (classification, summarization, question answering, RAG, etc.)
- Working with embeddings, vector search, and tools like Pinecone, Weaviate, or FAISS
- Designing services that are modular, debuggable, and scalable
- Collaborating with automation engineers and operators to productize ideas quickly
- Owning the lifecycle of AI-powered features — from design to deployment to monitoring
Other
- Are curious, fast, and biased toward building over theorizing
- Can explain the difference between a cool demo and a durable system
- Remote-first culture with async-friendly workflows
- Direct access to leadership & fast decision cycles
- Freedom to ship, test, and own high-impact projects
