Senior Full Stack Engineer - AI

Software Finder•201 District, VA

1d•Onsite

About The Position

We are looking for Full Stack Engineers with 5+ years of experience developing cutting-edge web apps from the ground up. You will be responsible for implementing the architecture and core features of our web app as well as maintaining the codebase. Building AI-powered automation, real-time data pipelines and customer facing products. You'll own features end-to-end: design APIs, build frontends, integrate LLMs, optimize databases, deploy to serverless and managed servers.

Requirements

5+ years of experience developing cutting-edge web apps from the ground up.
Experience implementing the architecture and core features of web apps.
Experience maintaining codebases.
Experience building AI-powered automation.
Experience building real-time data pipelines.
Experience building customer-facing products.
Experience owning features end-to-end: design APIs, build frontends, integrate LLMs, optimize databases, deploy to serverless and managed servers.
Proficiency in Node.js/TypeScript with NestJS, production APIs, RESTful design, JWT/OAuth, rate limiting, Swagger/OpenAPI.
Experience with async processing and queues (Bull/BullMQ, SQS, background jobs, retry logic).
Experience with ORMs (Prisma or TypeORM, migrations, relations, transactions).
Comfortable reading/writing Python (FastAPI/Flask) for microservices, async/await (not expert-level).
Proficiency in React/Next.js with TypeScript, hooks/lifecycle, performance optimization.
Experience with state management (Redux/NgRx/Zustand).
Experience with modern frontend stacks (Tailwind/Material/Bootstrap, REST/GraphQL/WebSockets, Jest/Cypress).
Proficiency in PostgreSQL with complex queries (joins/CTEs/window functions), EXPLAIN ANALYZE, indexing, schema design, and transactions.
Experience with Redis for caching patterns, session management, rate limiting, and pub/sub.
Production experience with LLM APIs (OpenAI/Anthropic/OpenRouter) including prompt engineering, token management, structured outputs, and error handling (rate limits/timeouts/retries).
Production experience with vector databases (Qdrant) for semantic search, embeddings, and similarity search.
Experience with NLP libraries (spaCy/NLTK/SentenceTransformers) for text processing.
Experience with Text-to-Speech (TTS) models (Elevenlabs or open-source).
Production deployment experience on AWS core services (EC2, RDS, S3, Lambda, SQS/SNS, CloudWatch).
Experience deploying and maintaining production apps on AWS.
Experience with AWS infrastructure (VPCs, security groups, IAM, cost optimization).
Experience debugging with CloudWatch.
Experience with Docker (multi-stage builds, Docker Compose, image optimization).
Experience with CI/CD pipelines (GitHub Actions/GitLab) for automated testing and deployment.
Experience developing 2-3 production applications serving real external users.
Experience with third-party API integrations at scale (rate limits, retries, circuit breakers, monitoring).
Experience implementing LLM features in production (actual API integration with error handling, not demos).
Experience deploying features to serverless/AWS and maintaining them in production.
Experience incorporating tests and documentation into the workflow.

Responsibilities

Implement the architecture and core features of our web app.
Maintain the codebase.
Build AI-powered automation.
Build real-time data pipelines.
Build customer-facing products.
Design APIs.
Build frontends.
Integrate LLMs.
Optimize databases.
Deploy to serverless and managed servers.
Implement Node.js/TypeScript backend with NestJS, production APIs, RESTful design, JWT/OAuth, rate limiting, and Swagger/OpenAPI.
Utilize async processing and queues with Bull/BullMQ, SQS, background jobs, and retry logic.
Work with ORMs like Prisma or TypeORM, including migrations, relations, and transactions.
Develop microservices using Python (FastAPI/Flask) with async/await.
Build frontends using React/Next.js with TypeScript, hooks/lifecycle, and performance optimization.
Implement state management with Redux/NgRx/Zustand.
Utilize modern frontend stacks including Tailwind/Material/Bootstrap, REST/GraphQL/WebSockets, and Jest/Cypress.
Manage PostgreSQL databases with complex queries (joins/CTEs/window functions), EXPLAIN ANALYZE, indexing, schema design, and transactions.
Implement Redis for caching patterns, session management, rate limiting, and pub/sub.
Integrate LLM APIs (OpenAI/Anthropic/OpenRouter) with prompt engineering, token management, structured outputs, and error handling.
Implement semantic search in production using vector databases like Qdrant, including embeddings and similarity search.
Utilize NLP libraries such as spaCy/NLTK/SentenceTransformers for text processing.
Integrate Text-to-Speech (TTS) models like Elevenlabs or open-source alternatives.
Deploy and maintain production applications on AWS core services (EC2, RDS, S3, Lambda, SQS/SNS, CloudWatch).
Manage AWS infrastructure including VPCs, security groups, IAM, and perform cost optimization.
Debug applications using CloudWatch.
Utilize Docker for multi-stage builds, Docker Compose, and image optimization.
Implement CI/CD pipelines with GitHub Actions/GitLab for automated testing and deployment.
Ensure tests and documentation are part of the workflow.