Senior Full - Stack Engineer

We are looking for a Senior Full-Stack Engineer to build scalable, AI-native products across frontend, backend, and cloud. You will own features end-to-end, contribute to technical decisions, and work closely with product and leadership teams.

Responsibilities:

• Build scalable applications using React, Next.js, Node.js, and TypeScript.
• Own features from architecture and development to deployment and optimization.
• Design secure APIs, backend services, authentication, and database structures.
• Integrate LLMs and generative AI into production applications.
• Build RAG pipelines involving ingestion, chunking, embeddings, retrieval, reranking, and grounded responses.
• Develop AI agents for multi-step task execution, tool usage, memory, and workflow automation.
• Work with LLM Ops, including model serving, deployment, GPU utilization, quantization, and inference optimization.
• Contribute to LLM fine-tuning, training data preparation, evaluation, and domain-specific model adaptation.
• Work with vector databases, cloud infrastructure, CI/CD, monitoring, and production systems.
• Debug, test, optimize, review code, and resolve production issues.
• Collaborate with product, design, and engineering teams to deliver reliable solutions.

Requirements:

• Bachelor's or master's degree in computer science or a related field.
• 2-4 years building production-grade applications in startup or product environments.
• Strong understanding of APIs, databases, authentication, and backend architecture.
• Hands-on experience with LLMs, RAG, vector databases, or AI agents.
• Understanding of LLM Ops and model deployment is a strong advantage.
• Exposure to LLM fine-tuning and model evaluation is preferred.
• Understanding of scalable systems, performance optimization, debugging, and reliability.
• Experience with cloud platforms and CI/CD workflows.
• Strong ownership, problem-solving, communication, and collaboration skills.

Skills

AI agent, AI agents, GenAI, LLM, LLMs, RAG, full stack, fullstack, generative AI, large language model, large language models, vector database, vector databases