About the role
We're looking for a Full-Stack Developer who is strong in MERN, confident in Python backends, and excited to work hands-on with AI-powered systems. You'll build user-facing features and the AI-enabled services behind them from creator feeds to intelligent recommendations.
Responsibilities:
AI-Powered Product Development:
- Integrate LLMs and AI services into product workflows (search, recommendations, assistants).
- Work with AI/ML engineers on RAG pipelines, embeddings, and inference APIs.
- Build backend services that power AI stylists, product tagging, and content intelligence.
Full-Stack Engineering
- Build end-to-end features using React / Next.js + Node.js + Python (FastAPI).
- Develop scalable REST APIs and microservices.
- Own features from design discussion to production rollout.
Backend and Data:
- Design APIs for feeds, reels, creators, products, and commerce.
- Work with MongoDB, Redis, and SQL databases.
- Build async jobs, webhooks, event pipelines, and background workers.
Frontend:
- Build fast, clean, and responsive UIs.
- Implement AI-driven UX patterns (smart suggestions, auto-tagging, search).
- Collaborate closely with product and design.
Engineering Excellence:
- Write clean, maintainable, well-tested code.
- Improve performance, scalability, and reliability.
- Participate in architectural decisions and code reviews.
Requirements:
- Hands-on with LangChain, Haystack, or similar.
- Experience with vector databases (FAISS, Pinecone, Weaviate).
- Exposure to computer vision or image/video pipelines.
- Startup or 01 product experience.
- Docker, CI/CD, basic cloud deployment (AWS/GCP/Azure).
Core Stack:
- 4-6 years of hands-on full-stack experience.
- Strong experience with: React.js / Next.js, Node.js (Express / NestJS), Python (FastAPI preferred).
- Solid understanding of REST APIs, auth (JWT/OAuth).
AI Awareness (Practical):
- Experience integrating AI/ML APIs into production systems.
- Familiarity with: LLMs (OpenAI, Mistral, LLaMA, Cohere), Prompt engineering basics, Embeddings and semantic search.
- Understanding of RAG concepts and AI inference workflows.
Data and Systems:
- MongoDB (schema design, aggregations).
- Redis / caching.
- Async processing and background jobs.