We’re an early-stage startup building intelligent, AI-driven tools that combine automation, design, and data to transform how teams operate. We move fast, iterate constantly, and believe in empowering engineers to own their work end-to-end — from concept to deployment.

Role Overview

We’re looking for an AI Engineer who can design, build, and deploy LLM-powered applications from scratch. You’ll work closely with our product and full-stack teams to architect intelligent backend systems, integrate APIs, and bring advanced AI capabilities into production.

This is a hands-on role for someone who thrives in startup environments — creative, pragmatic, and obsessed with turning new models and frameworks into tangible products that users love.

What You’ll Do

• Design and build AI-driven applications leveraging LLMs (OpenAI, Anthropic, or similar)
• Develop and maintain backend services using Python (FastAPI or Flask)
• Integrate LangChain, LlamaIndex, or similar frameworks to orchestrate prompts, tools, and memory
• Implement RAG (retrieval-augmented generation) pipelines using vector databases such as Pinecone, Weaviate, or FAISS
• Deploy and manage scalable inference services in AWS, Azure, or GCP
• Collaborate with full-stack engineers to expose APIs and integrate AI into user-facing tools
• Continuously evaluate and improve model performance, accuracy, and latency
• Stay up-to-date with the latest advancements in LLMs, embeddings, and AI infrastructure

What We’re Looking For

• 3+ years of experience in software engineering (startup or product environment preferred)
• Proven experience building and deploying LLM applications
• Strong Python programming skills and familiarity with backend frameworks (FastAPI, Flask)
• Experience with LangChain, OpenAI API, or similar orchestration frameworks
• Hands-on with cloud deployment, containerization (Docker), and vector databases
• Understanding of prompt engineering, context management, and evaluation frameworks
• Comfort working cross-functionally with product, design, and frontend teams
• Self-starter mindset — able to work autonomously and iterate quickly

Nice to Have

• Experience fine-tuning or evaluating open-source models (Llama, Mistral, etc.)
• Familiarity with frontend frameworks like React (for integration testing)
• Understanding of data pipelines and ETL processes
• Previous startup or 0-to-1 product experience

Why Join

• Build AI products from the ground up — not just plug into existing systems
• High ownership and autonomy in a fast-moving, collaborative startup
• Competitive compensation and equity
• Opportunity to shape the foundation of an emerging AI platform