Summary
✨ AI‑Generated
Build next-generation AI applications as a fully remote full-stack engineer. You’ll develop LLM-powered systems, RAG pipelines, AI agents, front-end experiences and backend APIs, while deploying production services on cloud infrastructure and applying modern CI/CD, IaC, containers, and Kubernetes practices.
Highlights
Fully remote role with global work flexibility, hands-on ownership of modern AI applications, exposure to LLMs and AI agents, and opportunities to work across cloud infrastructure, DevOps, and production reliability.
Description
Are you passionate about software development and eager to work on cutting-edge projects? Do you dream of working from anywhere in the world? Join us as a fully remote Full-Stack Developer and be part of building the next AI-powered application.
Responsibilities
Build end-to-end LLM applications, including data pipelines, vectorization, retrieval, and model orchestration.Develop RAG systems using vector databases and document retrieval frameworks.Build and maintain AI agents with tool use, multi-step workflows, and API integrations.Develop front-end interfaces and back-end APIs that integrate LLM and agent capabilities.Deploy and operate AI services on cloud platforms (GCP or AWS).Implement CI/CD, IaC, containerization, and Kubernetes-based deployments.Ensure system reliability, performance, and security for production AI applications.
Requirements
Bachelor’s degree in CS, Engineering, Data Science, or related field.5+ years of experience in full-stack or software engineering.Strong skills in React (front-end) and Python/Node.js (back-end).Experience with SQL/NoSQL databases and vector databases (e.g., Pinecone, Weaviate, FAISS).Hands-on experience building LLM apps using frameworks like LangChain or LlamaIndex.Familiarity with embeddings, retrieval, prompt engineering, and model evaluation.Experience deploying cloud-native apps on GCP or AWS.Proficiency with Docker, Kubernetes, CI/CD, and IaC (Terraform/CloudFormation).
Nice-to-Have
Experience fine-tuning or optimizing LLMs.Knowledge of multi-agent systems, reranking methods, and hybrid search.Experience with streaming systems (Kafka, Pub/Sub).
