Full Stack AI Engineer (LLM-based products) - Full-time - Overlap CET

Why This Opportunity

Join an ambitious AI startup building the next generation of intelligent software development. You'll help create an AI-powered platform that transforms natural language intent into production-ready systems—automatically generating APIs, user interfaces, tests, and deployment artifacts while maintaining enterprise grade governance and portability.

This is a senior engineering role for someone who enjoys solving complex technical challenges, navigating ambiguity, and taking ownership from architecture through production.

About the Company

We're a European AI startup building a next-generation application generation platform that enables organizations to transform ideas into production-ready software through AI-native development workflows. Our focus is on creating reliable, scalable systems that combine modern AI capabilities with robust engineering practices.

Why This Role Matters

This role sits at the core of our AI platform.

You'll help design and build the systems responsible for retrieval, reasoning, agent orchestration, and full-stack application delivery. Beyond implementing features, you'll help shape technical direction, challenge assumptions, and independently drive solutions that improve the reliability, quality, and performance of production AI systems.

We're looking for someone who thrives in ambiguous environments—someone who asks the right questions before writing code, takes ownership of technical decisions, and can clearly explain the reasoning behind every architectural choice.

What You'll Build

• Design and develop production-grade AI applications across both the frontend and backend.
• Build and maintain modern React/Next.js web applications and secure authentication workflows.
• Design and own scalable backend APIs using Python and FastAPI.
• Develop sophisticated Retrieval-Augmented Generation (RAG) systems using vector databases and hybrid retrieval strategies.
• Build AI agents capable of multi-step reasoning, tool calling, structured outputs, and autonomous workflows.
• Evaluate and continuously improve AI systems by measuring answer quality, factual accuracy, latency, and operational cost.
• Design robust agent pipelines with reliable state management and error handling.
• Build and operate cloud-native services running on AWS.
• Design scalable PostgreSQL schemas, manage database migrations, and optimize application performance.
• Collaborate closely with a highly technical team to refine requirements, challenge assumptions, and deliver production-ready solutions.

Who We're Looking For

Must Have

• 5+ years of professional software engineering experience, including at least 2 years building production LLM-powered applications. Exceptional candidates with fewer years but demonstrated independent ownership will also be considered.
• Strong experience building and maintaining production full-stack applications using React, Next.js, and TypeScript.
• Professional experience designing and owning backend services using Python and FastAPI, including asynchronous programming patterns and production API design.
• Hands-on experience deploying and operating services on AWS ECS or AWS Fargate, including:
  *Docker
  *Amazon ECR
  *Application Load Balancer (ALB)
  *IAM
  *AWS Secrets Manager
  *CloudWatch
• Experience designing PostgreSQL schemas and managing database migrations using tools such as SQLAlchemy, Alembic, or equivalent.
• Proven experience building production AI systems involving:
  *Retrieval-Augmented Generation (RAG)
  *Vector databases
  *Agent loops
  *Tool calling
  *Structured outputs
• AI evaluation pipelines focused on quality, accuracy, latency, and cost
• Demonstrated ability to independently scope, question, design, build, and ship complex technical solutions without requiring detailed implementation guidance.
• Strong communication skills with the confidence to challenge unclear requirements, clarify ambiguity, and explain architectural decisions.
• Ability to maintain a fixed daily overlap of five contiguous hours with Central European business hours.

Nice to Have

• Experience with Model Context Protocol (MCP) servers, clients, tools, or resources.
• Experience using graph databases such as Neo4j.
• Experience with AI frameworks including:
  *LangGraph
  *LangChain
  *LlamaIndex
  *Semantic Kernel
  *Similar orchestration frameworks
• Experience building asynchronous or event-driven systems using technologies such as:
  *Celery
  *Temporal
  *Amazon SQS
• Strong testing practices using Pytest, Playwright, Jest, or equivalent.
  Experience with:
  *Terraform
  *AWS CDK
  *Redis
  *OpenSearch
  *Elasticsearch
  *Kubernetes
  *WebSockets
  *Real-time applications
• Experience working in early-stage startups or high-growth product environments.

Why You'll Enjoy Working Here

• Work on cutting-edge AI systems with significant technical ownership.
• Help define architecture for a rapidly evolving AI platform.
• Collaborate with a highly technical team solving challenging engineering problems.
• Fully remote engagement with long-term potential.
• Ongoing engagement with quarterly reviews and opportunities for continued impact.

Hiring Process

• Two live technical interview rounds (No AI assisting)
• No take-home assignment or prepared presentation required.
• Interviews focus on real-world engineering experience, technical reasoning, and independent problem-solving.