R-02 Claude Enterprise Agentic AI Ecosystem Engineer

Ariana.Digital is a team of entrepreneurial, energetic, and innovative digital professionals. We bring broad experience across industries and the digital ecosystem, helping organizations drive impact and sustainable growth. Our team thrives on diversity of backgrounds, skills, and experiences, and we value those who deliver tactical excellence along with a long-term strategic vision for our clients. https://ariana.digital

What We Offer: Flexible working arrangements Resources and support for continuous growth

Do you have experience in Teamwork?, We’re assembling the A-team for the agentic era. We are seeking a highly skilled and motivated R-02 level expert in the Anthropic Claude ecosystem, with a strong focus on Model Context Protocol (MCP) and Agentic AI development.

This pivotal role will be instrumental in shaping the future of our AI-powered solutions, leveraging the power of Claude to create innovative and impactful applications. You will be responsible for designing, developing, and deploying cutting-edge AI agents, ensuring their safe, reliable, and efficient operation within our existing infrastructure. As a key member of our AI team, you will collaborate closely with researchers, engineers, and product managers to translate complex business requirements into robust and scalable AI solutions. A deep understanding of prompt engineering, LLM fine-tuning, and AI safety principles is essential.

The successful candidate will possess exceptional problem-solving abilities, strong communication skills, and a proven track record of delivering high-quality AI products. This role offers a unique opportunity to work at the forefront of AI technology, contributing to groundbreaking advancements in Agentic AI.

If you are passionate about pushing the boundaries of what’s possible with AI and have a proven ability to deliver results, we encourage you to apply., * Proven experience with Anthropic Claude and its API.* Deep understanding of Agentic AI concepts and development techniques.* Proficiency in prompt engineering and LLM fine-tuning.* Solid understanding of Model Context Protocol (MCP) principles and implementation.* Strong programming skills in Python.* Experience with TensorFlow and/or PyTorch.* Demonstrated commitment to AI safety and ethical considerations.* Excellent problem-solving, communication, and collaboration skills.

Technical Expertise

• Deep understanding of Generative AI foundations, including:
• Prompt engineering and chaining techniques
• Retrieval-Augmented Generation (RAG) pipelines
• Agentic frameworks (e.g., LangChain, CrewAI, AutoGen)
• Vector databases (e.g., Pinecone, Weaviate, FAISS)
• Embeddings and fine-tuning approaches
• Evaluation tools and implementation of safety/guardrails
• Proficiency in backend development and orchestration with modern stacks (e.g., Python, Node.js, FastAPI, async workflows)
• Experience with API design, version control (Git), testing frameworks, and CI/CD pipelines

Anthropic Claude; Agentic AI; Prompt Engineering; Model Context Protocol (MCP); Python; TensorFlow; PyTorch; LLM Fine-tuning; AI Safety; Natural Language Processing; Problem Solving; Communication

Systems Thinking & Architecture

• Strong ability to design modular, scalable GenAI systems using composable building blocks
• Familiarity with graph databases, reasoning layers, and LLM-based inference strategies

AI-Augmented Development

• Comfort using AI tools (e.g., GitHub Copilot, code agents) to accelerate coding and design workflows

Collaboration & Product Focus:

• Demonstrated ability to work cross-functionally with product managers and designers to build intuitive user experiences
• Comfort in fast-paced, ambiguous, and experimental environments

Communication

• Strong written and verbal communication skills to articulate technical decisions and collaborate effectively with distributed teams

Preferred Qualifications

• Experience with other open-source LLMs , including model customization or fine-tuning
• Familiarity with LLMOps tools and scalable AI deployment architectures, including containerization (Docker), orchestration (Kubernetes), and monitoring
• Contributions to open-source GenAI libraries, tools, or research, or active participation in the AI/ML community
• Prior work involving synthetic data generation, model evaluation frameworks, or benchmarking GenAI systems
• Knowledge of multimodal interfaces, including voice, vision, or agentic browsing and tool integration
• Exposure to knowledge graphs and structured reasoning techniques integrated with LLMs
• Strong UX instincts or product-oriented mindset - ability to bridge the gap between technical solutions and user value
• Experience building AI solutions in enterprise or regulated environments (e.g., healthcare, finance, government)

$50 - $75 an hour - Contract