Senior AI Agent Engineer 

<p><strong>Senior AI Agent Engineer&nbsp;</strong></p> <p><strong>We are</strong></p> <p>Wizeline is a global AI-native technology solutions provider that develops cutting-edge, AI-powered digital products and platforms. We partner with clients to leverage data and AI, accelerating market entry and driving business transformation. As a global community of innovators, we foster a culture of growth, collaboration, and impact.</p> <p>With the right people and the right ideas, there's no limit to what we can achieve.</p> <p><strong>Are you a fit?</strong></p> <p>We're looking for a Senior AI Agent Engineer with a passion for building production-grade, tool-augmented AI agents that blend cutting-edge LLM techniques with solid software-engineering discipline. In this role, you'll design multi-step reasoning pipelines, wire them to business systems, and harden them for scale, safety, and maintainability — helping enterprise customers launch conversational agents that solve real problems, take real actions, and comply with real-world policies.</p> <p>You'll play a key role in agent design and delivery, tool and data integration, LLM orchestration and planning, and continuous optimization — owning the full agent development life-cycle from scoping through monitoring and iterative tuning.</p> <p>If you're passionate about AI R&amp;D, agentic systems, and building reliable, guard-railed AI products, we'd love to meet you.</p> <p><strong>Qualifications:</strong></p> <ul> <li>Excellent communication and collaboration skills. English B2 Advanced or C1</li> <li>5+ years of software engineering experience in production environments (TypeScript/Node, Go, or Python) with strong API design, testing, and debugging habits</li> <li>Hands-on LLM experience (GPT, Claude, Gemini, or fine-tuned OSS models): prompt engineering, function/tool calling, model selection, and evaluation</li> <li>Retrieval-Augmented Generation (RAG): designing embedding pipelines and semantic search with Pinecone, Weaviate, etc.</li> <li>Agent orchestration expertise: LangChain/LangGraph, OpenAI Agents SDK, CrewAI, or equivalent frameworks for tool-augmented reasoning loops</li> <li>ML-/DevOps literacy: containerization, CI/CD, GPU/AI infra, caching, automated evals for nondeterministic systems</li> <li>Experience enforcing security guardrails &amp; PII protection in user-facing AI products</li> </ul> <p><strong>Nice-to-have</strong></p> <ul> <li>Real-time/voice agent delivery (e.g., SSE or WebSockets)</li> <li>Familiarity with emerging multi-agent protocols (MCP, A2A) or supervisor/critique agent patterns</li> <li>Domain experience in e-commerce, fintech, telecom, or large-scale customer support</li> <li>Prior work with automated prompt/agent regression testing frameworks</li> </ul> <p><strong>Why You'll Love This Role</strong></p> <ul> <li>Build cutting-edge, tool-augmented AI agents at the intersection of AI R&amp;D and backend engineering</li> <li>Work on multi-model orchestration, agentic reasoning loops, and enterprise-grade AI systems</li> <li>Collaborate with highly skilled engineers in an AI-native technology company</li> <li>Influence technical decisions and contribute to AI engineering best practices</li> <li>Enjoy continuous learning, professional development, and global collaboration opportunities</li> </ul> <p><strong>What We Offer</strong></p> <ul> <li>A High-Impact Environment</li> <li>Commitment to Professional Development</li> <li>Flexible and Collaborative Culture</li> <li>Global Opportunities</li> <li>Vibrant Community</li> <li>Total Rewards</li> </ul> <p>Specific benefits are determined by employment type and location. Find out more about our culture <a href="https://www.instagram.com/wizelineglobal/">here</a></p>