Description

Design, build, and deploy generative AI applications by combining large language models with scalable full-stack architectures.

This role is on-site.

Responsibilities

• Develop responsive front-end interfaces using React, Vue, or Angular to visualize AI outputs and manage user interactions.
• Build Python-based backend services and APIs to interface with LLMs, vector databases, and external data sources.
• Implement Retrieval-Augmented Generation (RAG) systems and prompt engineering frameworks to ensure consistent model behavior.
• Establish CI/CD pipelines and MLOps practices for monitoring, logging, and cost-effective deployment of AI inference services.

Required Skills

• 3+ years of full-stack development experience with JavaScript/TypeScript and Python.
• 1+ years of hands-on experience with generative AI technologies and LLM integration.
• Proficiency with major LLM frameworks such as LangChain or LangGraph.
• Experience with vector databases (Pinecone, MongoDB, FAISS) and embedding models.
• Strong understanding of REST APIs, microservices architecture, and containerization (Docker, Kubernetes).
• Experience with cloud platforms (AWS, Azure, GCP) and CI/CD tools like GitHub Actions.
• Bachelor’s degree in Computer Science, Software Engineering, AI/ML, or a related field.

Preferred Skills

• Experience developing commercial AI applications or products.
• Knowledge of AI safety practices, responsible AI deployment, and evaluation metrics.

Key Skills

Education

Bachelor’s degree