Job Title

Location: Remote (India preferred)Type: Full-TimeStart Date: ImmediateCompensation: Cash + potential equity (based on contribution)About the RoleWe’re building a next-gen AI product that blends large language models, memory systems, and behavior modeling to deliver high-impact outcomes across team performance, communication, and learning.We’re already live in production and looking for one exceptional engineer to help us go faster, smarter, and deeper into AI-native experiences.What You’ll OwnBuild and improve AI agents using OpenAI APIs (GPT-4), memory storage, and dynamic prompt systemsArchitect and debug flows connecting LLMs with real-world use cases (Slack, files, messages, user states)Implement and optimize vector search pipelines (Pinecone or pgvector) for RAG systemsDesign, test, and iterate coaching or decision-making logic that evolves with user behaviorWork closely with the founder to ship features weekly — no silos, no hierarchyWhat We’re Looking For1–3 years of experience in AI/ML, backend, or full-stack rolesProficient in Node.js, PostgreSQL/Supabase, and OpenAI API usageSolid grounding in LLM integration, prompt engineering, and memory/embedding systemsQuick learner who writes clean, debug-friendly codeBonus: Slack APIs, LangChain, Pinecone, Teams bots, Render/Vercel deploymentEven bigger bonus: you think before you code, ship fast, and can explain your logic clearlyWhat You GetOwnership: Be the second technical teammate in a real AI productGrowth: Learn systems design, prompt architecture, and agent orchestration hands-onImpact: Your code runs in production from day one — no busyworkTrajectory: If we click, you’ll shape this product with us as a core technical brain