Senior AI Engineer - AWS

We're looking for a Senior AI Engineer who can own the design and delivery of complex AI systems on AWS. You'll be leading the architecture and hands-on build of production-grade AI solutions: advanced RAG pipelines, short-term and long-term memory management, multi-agent orchestration, prompt engineering at a systems level, and governed knowledge retrieval. If you enjoy solving hard infrastructure problems at the intersection of AI and cloud, you'll feel at home with us.

This isn't prompt engineering. It's building the infrastructure that makes AI systems genuinely useful at enterprise scale.

What you'll bring / Tech Stack

• 2+ years of hands-on experience building AI/ML systems in production
• Deep understanding of RAG pipelines: chunking strategies, embedding models, hybrid retrieval, re-ranking, and context window management
• Strong experience with AWS AI/ML services: Bedrock, SageMaker, OpenSearch, DynamoDB, Lambda, Step Functions, EventBridge
• Solid software engineering skills in Python and/or TypeScript — you write clean, testable, production-ready code
• Experience with containerization and orchestration (Docker, EKS/ECS)
• Understanding of prompt engineering at a systems level: template design, token budgeting, dynamic prompt construction
• Familiarity with multi-agent architectures: agent orchestration, shared memory patterns, event-driven coordination between AI components (LangChain, Strands)
  

What you'll do

• Lead the technical design and implementation of cloud-native AI systems on AWS for our clients
• Build and optimize hybrid RAG pipelines that combine semantic vector search with structured retrieval, with governance controls on what gets retrieved and how
• Design and implement memory management systems, persistent, contextual knowledge layers that AI agents can read from and write to across sessions and workflows
• Architect prompt management services that handle token budgeting, dynamic context injection, and template-based generation
• Build data ingestion pipelines: document parsing, automated metadata extraction, embedding generation, and indexing
• Collaborate with clients and internal teams to turn complex requirements into actionable technical plans
• Mentor other engineers on AI/ML best practices and emerging patterns

Work setup

Fully remote, with the option for occasional in-person meetups (if you’d like).

Salary range

2 000 000 - 3 000 000 HUF gross