AI Full Stack Engineer

Role Overview

We are seeking an AI Full Stack Engineer to design, build, and deploy production-grade applications that combine modern web technologies with artificial intelligence and large language models (LLMs).

The ideal candidate is comfortable working across the entire technology stack—from frontend interfaces and backend APIs to databases, cloud infrastructure, AI models, retrieval systems, and agentic workflows. You will work closely with product, engineering, and AI teams to turn AI capabilities into reliable, scalable, and intuitive products.

Key Responsibilities

• Design and develop end-to-end AI-powered web applications.

• Build responsive frontend applications using technologies such as React, Next.js, TypeScript, HTML, and CSS.

• Develop scalable backend services and APIs using Python, FastAPI, Node.js, or similar frameworks.

• Integrate LLMs and AI APIs such as OpenAI, Anthropic, Gemini, or open-source models into production applications.

• Develop RAG (Retrieval-Augmented Generation) pipelines using embeddings, document processing, semantic search, and vector databases.

• Build AI agents and tool-calling workflows capable of interacting with databases, APIs, and external systems.

• Design prompt workflows, structured outputs, evaluation pipelines, and guardrails for LLM applications.

• Implement streaming AI responses and real-time application experiences.

• Design and manage relational, NoSQL, and vector databases such as PostgreSQL, MongoDB, Redis, Pinecone, Weaviate, or pgvector.

• Develop authentication, authorization, role-based access control, and secure API integrations.

• Build asynchronous and background-processing systems for computationally intensive AI workloads.

• Deploy and operate applications using cloud platforms such as AWS, Azure, or Google Cloud.

• Containerize and deploy applications using Docker, Kubernetes, serverless platforms, or managed cloud services.

• Implement CI/CD pipelines, automated testing, logging, monitoring, and observability.

• Optimize AI applications for latency, accuracy, reliability, token usage, and cost.

• Evaluate model performance using automated evaluations, test datasets, and human feedback.

• Troubleshoot production issues across frontend, backend, infrastructure, data, and AI components.

• Collaborate with product managers and designers to translate product requirements into technical solutions.

• Stay current with developments in generative AI, LLMs, AI agents, multimodal models, and related technologies.

Required Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, or equivalent practical experience.

• Strong software engineering fundamentals, including algorithms, data structures, APIs, databases, and distributed systems.

• Professional experience with Python and/or TypeScript/JavaScript.

• Experience with modern frontend frameworks such as React or Next.js.

• Experience developing backend APIs using frameworks such as FastAPI, Django, Flask, Express, NestJS, or similar technologies.

• Experience working with REST APIs and/or GraphQL.

• Strong knowledge of relational databases such as PostgreSQL or MySQL.

• Experience integrating third-party APIs and cloud services.

• Familiarity with Git, automated testing, CI/CD, Docker, and cloud deployment.

• Experience developing applications using LLMs or generative AI APIs.

• Understanding of prompt engineering, embeddings, semantic search, and RAG architectures.

• Strong debugging and problem-solving skills.

Preferred Qualifications

• Experience with OpenAI APIs, Anthropic Claude, Google Gemini, Hugging Face, or open-source LLMs.

• Experience with AI frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, or equivalent frameworks.

• Experience building AI agents, multi-agent systems, tool calling, and workflow orchestration.

• Experience with vector databases and technologies such as pgvector, Pinecone, Qdrant, Weaviate, Chroma, or Elasticsearch.

• Knowledge of LLM evaluation, tracing, prompt versioning, hallucination mitigation, and AI observability.

• Experience with multimodal AI involving text, images, audio, or video.

• Experience implementing model context protocols, structured outputs, function calling, or external AI tools.

• Understanding of machine learning concepts, transformers, embeddings, fine-tuning, and model inference.

• Experience deploying applications on AWS, Azure, GCP, Vercel, Kubernetes, or similar platforms.

• Familiarity with event-driven architectures, queues, caching, and asynchronous processing.

Typical Technology Stack

Frontend:

React, Next.js, TypeScript, Tailwind CSS

Backend:

Python, FastAPI, Node.js, REST APIs, WebSockets

AI / LLM:

OpenAI, Anthropic, Gemini, Hugging Face, LangChain, LangGraph, LlamaIndex

Data:

PostgreSQL, MongoDB, Redis, pgvector, Pinecone, Qdrant, Elasticsearch

Infrastructure:

AWS / Azure / GCP, Docker, Kubernetes, Vercel, GitHub Actions, Terraform