Senior Full-Stack Developer with LLM

📎 About the company

Akveo is an IT company specializing in web, mobile, low-code, and AI solutions for clients in the USA and Europe. We develop high-quality software products that help businesses automate processes and implement innovations. We are actively expanding into AI-driven solutions, leveraging artificial intelligence to enhance our products and services.

Akveo is a team of 100+ professionals. We have development centers in Poland and Lithuania, and representatives in the US.

We are looking for a Senior Full-Stack Developer with experience in LLM as Akveo is launching new AI projects. You will help strengthen and develop expertise in building intelligent assistants powered by LLM.

Project examples:

• AI Language Learning Platform - a language assistant powered by OpenAI, a SaaS platform with user management and payment integration.
  
• AI Personal Coach Assistant - an AI chat for goal setting, task tracking, and reminders, built as a PWA with Next.js and Supabase.
  

📎 General Requirements:
Must have:‍

- Proficiency in TypeScript

- Experience with Docker

- Understanding of CI/CD pipelines

- Building and maintaining RESTful APIs

- Deploying / maintaining applications on AWS
Nice to have:

- Experience with GraphQL

- Familiarity with Kubernetes or Terraform

- Serverless architectures (AWS, Supabase)‍

‍

Frontend Requirements:
Must have:

- Experience with React and Next.js

- State management using React Query, Zustand, or Redux Toolkit

- Familiarity with API integration and component-based architecture
Nice to have:

- Styling with Tailwind

- Experience with modern UI libraries like shadcn/ui

- Working knowledge of WebSockets or other real-time communication methods‍

‍

Backend Requirements:
Must have:

- Proficiency in Node.js (Express, Fastify, or NestJS)

- Solid experience with PostgreSQL

- ORM knowledge (Prisma or Drizzle)
- Strong understanding of API architecture, authentication, and error handling
Nice to have:

- Experience with MongoDB

- Familiarity with queues and background jobs (Redis, BullMQ, RabbitMQ)

- Knowledge of caching, rate limiting, and webhook handling
‍

‍LLM Requirements:
Must have:

- Understanding of LLM fundamentals: models, prompts, context, temperature, tokens, embeddings, agents, RAG, tools

- Ability to design effective prompts and manage contextual information

- Awareness of model APIs (OpenAI, Anthropic...)
Nice to have:

- Hands-on experience with LangChain, Mastra AI, AI SDK

- Experience creating simple LLM agents (tools, chains, memory...)

- Familiarity with vector stores (PGVector, Pinecone...)

- Ability to build RAG pipelines (data chunking, embeddings, retrieval)
‍

📎 Responsibilities:

• Architect and launch new projects: design structure, select technologies from scratch.
• Communicate with customers: gather requirements, define scope, and translate business goals into technical solutions.
• Develop and maintain full-stack features: from API to UI, ensuring scalability, security, and performance.
• Lead code quality and best practices: review code, mentor other developers.
• Own the system lifecycle: oversee deployment, troubleshooting, and continuous improvement.

📎 What can we offer?

• Quick hiring process (2 interviews till final offer).
• Flexible work schedule and work from any convenient location.
• Loyal clients that trust our technical expertise and give us the freedom of professional self-expression.
• Compensation for training and certification.
• Performance Review system (meetings every 6 months), 1:1 rallies.

Join us!)

‍