AI Engineer

Key Responsibilities

• Design and implement agent-based systems and workflow orchestration using LangGraph as the primary framework, with Strands leveraged for rapid AWS/Bedrock-native prototyping where appropriate.
• Architect and implement A2A-compliant systems — covering Agent Cards, task handling, and inter-agent messaging — to enable interoperability across distributed agent networks.
• Develop prototypes, proofs-of-concept (PoCs), and minimum viable products (MVPs) rapidly to validate AI-driven solutions and de-risk early-stage product decisions.
• Build and maintain multi-modal AI systems that integrate text, image, and structured data — ensuring robust, scalable, and production-ready implementations.
• Stay current with the fast-moving AI landscape, proactively evaluating new models, tools, and frameworks.

Required Qualifications

• 5+ years of Python with solid software engineering fundamentals.
• 2+ years of hands-on AI engineering experience, including building and shipping production AI or ML systems.
• Proven hands-on experience with LangGraph — graph-based agent design, state management, and human-in-the-loop workflows.
• Solid understanding of the A2A protocol — including Agent Cards, task lifecycle, and inter-agent communication patterns. Awareness of agent-specific operational concerns such as agent-to-agent latency, agent security (authentication, authorization, and trust boundaries between agents), and reliability patterns in distributed agent systems. Hands-on implementation experience is a strong plus.
• Understanding of MCP (Model Context Protocol) and how to use it alongside A2A — knowing when to apply each protocol in a multi-agent system.
• Practical experience on AWS and/or Google Cloud Platform — including AI/ML services such as SageMaker, Vertex AI, and Bedrock, as well as core infrastructure including Lambda, Cloud Run, S3, and BigQuery.
• Strong understanding of LLM fundamentals: prompt engineering, retrieval-augmented generation (RAG), embeddings, fine-tuning, and evaluation methodologies.
• Experience with vector databases and semantic search (OpenSearch, pgvector, Pinecone, or similar).
• Excellent communication skills — ability to work collaboratively in a remote, async-friendly environment. We operate primarily across EST and CET time zones, so overlap with both is expected.
• A public portfolio of AI work — GitHub projects, demos, papers, or other evidence of shipped work. We want to see what you’ve built.

Nice to Have

• Experience with Strands, AWS's agent SDK for fast prototyping on Bedrock.
• Experience working directly with clients or in a consulting/agency environment.
• Background in NLP, computer vision, or structured data modeling as a complement to generative AI work.

What We Offer

• We Offer Fully remote with flexible hours — work from anywhere with meaningful overlap across EST and CET.
• The opportunity to be part of the AI transformation at US-based clients — from fast-moving startups to Fortune 500 enterprises — working on production systems with real organizational impact.
• A collaborative, engineering-first culture that values craftsmanship, curiosity, and continuous learning.
• Competitive compensation.
• Access to the latest AI tools, cloud credits, and learning resources to keep your skills sharp.

How to Apply

Submit your resume, a brief note on a recent AI project — what you built, the challenge, and the outcome — and a link to your GitHub, portfolio, or demos. Applications without a portfolio will not be considered. A2A or MCP experience? We’d especially love to hear about it.