Qode
Full-Stack Lead - GenAI & LLM Applications
Qode, San Francisco, California, United States, 94199
Job Opening: Full-Stack Lead - GenAI & LLM Applications
Location: South San Francisco (SSF) - Hybrid - 3 days onsite
Start Date: Immediate
About the Role
We are seeking a hands-on Full-Stack Developer with Generative AI expertise to join our team and lead the development of a real-time AI application leveraging AWS serverless architecture, FastAPI, and LLM-based pipelines. The ideal candidate is a builder with a deep understanding of full-stack development, cloud-native applications, and AI-powered user experiences.
Your Responsibilities • Build and enhance React-based frontends hosted on CloudFront • Design scalable, low-latency APIs using FastAPI (Python) integrated with API Gateway (REST + WebSocket) • Develop AWS Lambda functions for backend services, data handling, and orchestration • Hands-on experience with OpenSearch for implementing scalable search functionality • Manage authentication using SSO, and enable secure access flows • Integrate real-time WebSocket interfaces for LLM streaming and dashboarding • Work closely with data science teams to connect LLM pipelines (LangChain + RAG) and vector search mechanisms • Design and maintain serverless data layers using DynamoDB, Aurora PostgreSQL, Athena, and S3 • Participate in CI/CD automation using GitHub Actions, CloudFormation/CDK, and manage IAM roles/policies • Collaborate on data pipelines using AWS Glue, Airflow (MWAA), and Sagemaker for model training/inference
Key Technologies • Frontend: React, TypeScript, CloudFront • Backend: FastAPI (Python), AWS Lambda, API Gateway (REST + WebSocket), Cognito • Search & Storage: OpenSearch, DynamoDB, Aurora PostgreSQL, S3, Athena • GenAI & RAG: LangChain, FAISS, Pinecone, OpenAI, Claude, AWS Bedrock • Data Engineering: AWS Glue, Airflow (MWAA) • DevOps: GitHub Actions, CloudFormation/CDK, IAM Roles • Streaming & Realtime: WebSockets, LLM streaming pipelines
You Should Have • Proven experience in building production-grade GenAI features using LLM APIs and RAG pipelines • Hands-on experience with serverless app development on AWS • Solid understanding of FastAPI, microservices architecture, and REST/WebSocket API design • Comfort with both structured data (PostgreSQL) and NoSQL (DynamoDB) • Experience working in a CI/CD DevOps environment with infrastructure-as-code • Excellent problem-solving skills, and ability to troubleshoot complex cloud-native systems
Location: South San Francisco (SSF) - Hybrid - 3 days onsite
Start Date: Immediate
About the Role
We are seeking a hands-on Full-Stack Developer with Generative AI expertise to join our team and lead the development of a real-time AI application leveraging AWS serverless architecture, FastAPI, and LLM-based pipelines. The ideal candidate is a builder with a deep understanding of full-stack development, cloud-native applications, and AI-powered user experiences.
Your Responsibilities • Build and enhance React-based frontends hosted on CloudFront • Design scalable, low-latency APIs using FastAPI (Python) integrated with API Gateway (REST + WebSocket) • Develop AWS Lambda functions for backend services, data handling, and orchestration • Hands-on experience with OpenSearch for implementing scalable search functionality • Manage authentication using SSO, and enable secure access flows • Integrate real-time WebSocket interfaces for LLM streaming and dashboarding • Work closely with data science teams to connect LLM pipelines (LangChain + RAG) and vector search mechanisms • Design and maintain serverless data layers using DynamoDB, Aurora PostgreSQL, Athena, and S3 • Participate in CI/CD automation using GitHub Actions, CloudFormation/CDK, and manage IAM roles/policies • Collaborate on data pipelines using AWS Glue, Airflow (MWAA), and Sagemaker for model training/inference
Key Technologies • Frontend: React, TypeScript, CloudFront • Backend: FastAPI (Python), AWS Lambda, API Gateway (REST + WebSocket), Cognito • Search & Storage: OpenSearch, DynamoDB, Aurora PostgreSQL, S3, Athena • GenAI & RAG: LangChain, FAISS, Pinecone, OpenAI, Claude, AWS Bedrock • Data Engineering: AWS Glue, Airflow (MWAA) • DevOps: GitHub Actions, CloudFormation/CDK, IAM Roles • Streaming & Realtime: WebSockets, LLM streaming pipelines
You Should Have • Proven experience in building production-grade GenAI features using LLM APIs and RAG pipelines • Hands-on experience with serverless app development on AWS • Solid understanding of FastAPI, microservices architecture, and REST/WebSocket API design • Comfort with both structured data (PostgreSQL) and NoSQL (DynamoDB) • Experience working in a CI/CD DevOps environment with infrastructure-as-code • Excellent problem-solving skills, and ability to troubleshoot complex cloud-native systems