About Wise Pirates
Wise Pirates is a leading Digital, Tech, and AI Business Partner, operating in over 80 countries from Portugal. With a team of 100+ professionals, we are a Martech-independent agency at the forefront of innovation in Southern Europe. Our ambition is to lead an AI-first marketing ecosystem, blending human creativity with the power of artificial intelligence.
We are dynamic, forward-thinking, and driven by data, automation, and meaningful customer experiences. We believe that our people are our most valuable asset, and we are committed to fostering a culture where they can grow, innovate, and thrive.
About the role
We are looking for a highly innovative and technically skilled AI Agents / Agentic Specialist to join our Process Automation Team. This crucial role focuses on leveraging cutting-edge Generative AI and Large Language Models (LLMs) to design, build, and deploy sophisticated AI Agents and agentic workflows that address complex business challenges in customer experience, marketing, sales, and internal operations.
The ideal candidate blends strong software engineering principles with deep knowledge of prompt engineering, LLM orchestration, and MLOps best practices. You will be responsible for transforming proof-of-concept AI ideas into production-ready, scalable agents that act autonomously, communicate effectively, and provide measurable value. This role demands a market-first, data-driven approach, where you are comfortable experimenting, iterating fast, and building novel solutions with a global reach.
Key Responsibilities:
Architecting Agentic Systems: Design and implement multi-step, multi-agent systems and agentic frameworks (e.g., using LangChain, Dify, N8N, LlamaIndex, or custom solutions) that perform complex tasks, including tool use, memory management, planning, and self-correction.
LLM Orchestration: Select, fine-tune, and integrate various LLMs and foundation models (Gemini, OpenAI, Anthropic, etc.) to optimize agent performance, latency, and cost efficiency.
Prompt Engineering Mastery: Develop and refine advanced prompt engineering strategies, including few-shot learning, Chain-of-Thought (CoT), and RAG (Retrieval-Augmented Generation) techniques to ensure agents deliver high-quality, relevant, and accurate outputs.
Scalable Deployment: Deploy and manage production-grade AI agents, focusing on scalability, security, and low latency, primarily utilizing cloud platforms (GCP preferred, or Azure/AWS).
Tool Integration: Equip agents with the necessary tools, APIs, and access to internal systems and databases, enabling them to execute real-world actions and retrieve real-time data. Ideally, knowledge in tools such as Lovable, or other AI-powered app development platform that is built around and integrates multiple LLMs
MLOps for Agents: Apply MLOps principles to monitor agent performance, manage version control for prompts and models, and establish continuous feedback loops for iterative refinement.
Proof-of-Concept & Experimentation: Lead research and development sprints to test emerging AI Agent capabilities, micro-LLMs, and new model architectures to maintain a competitive edge.
Cross-functional Collaboration: Work closely with engineering, product, and business teams to identify high-impact use cases and integrate AI agents into existing commercial products and workflows (including low-code automation platforms).
Ethical AI: Ensure all developed agents comply with ethical guidelines, data privacy laws, and industry standards, focusing on transparency and control.
What we are looking for
Minimum 1 year of experience in Machine Learning Engineering, Software Development, or AI/NLP specialization, with a dedicated focus on building and deploying LLM-based applications.
Expertise in Python and strong software engineering fundamentals (OOP, testing, version control with Git, CI/CD).
Proven hands-on experience with LLM orchestration frameworks (e.g., LangChain, LlamaIndex, Dify), RAG implementation, and prompt engineering.
Familiarity with major LLM APIs and models (OpenAI/GPT, Gemini/Google AI Studio, Anthropic/Claude).
Experience with MLOps tools and practices for monitoring, logging, and deploying ML/AI models (e.g., MLflow, Kubeflow, Vertex AI, Azure Machine Learning).
Experience deploying solutions on cloud platforms (GCP, Azure, or AWS), focusing on serverless and containerized deployment (e.g., Docker, Kubernetes).
Solid understanding of data modeling, data transformation, and ETL processes to prepare data for RAG and agent context.
Behavioral Skills
Innovator and Builder: A strong bias towards action and an innate drive to build novel, market-ready solutions rather than just research.
Systematic Problem Solver: Ability to handle the complexity and non-determinism of agentic systems, designing robust fallbacks and validation layers.
Business Translator: Excellent communication skills to bridge the gap between complex AI capabilities and tangible business outcomes.
Ambition and Agility: Thrives in a fast-paced R&D environment, capable of quick iteration, pivoting strategies, and managing the ambiguity of new technologies.
Detail-Oriented: Meticulous approach to prompt design, performance measurement, and ensuring model reliability.
Analytical Mindset : We are looking for someone that is capable to put data first and is obsessed with analytical initiatives and insights building, always with client satisfaction and business results in mind;
AI Readiness: Interest and nativeness in using AI as a partner to deliver efficient value, respecting security and privacy regulations;
Innovation Lover: Someone seeking for permanent growth and desiring to be part of innovative solutions
Results-Oriented Zeal: An unwavering commitment to the client's bottom line. You are expected to push boundaries, not just to secure environments, but to optimize them, chasing best overall performance and business goals to deliver maximum value in every interaction.
Nice to have
Experience with Google Cloud Platform services (Vertex AI, Dataflow, BigQuery, Generative AI Studio, Gemini API).
Deep knowledge of fine-tuning or training specialized LLMs or small language models (SMLs).
Contributions to open-source ML/AI projects or relevant academic publications.
Experience in AdTech, MarTech, or Customer Experience (CX) domains.
Professional certifications in Machine Learning or Cloud AI platforms.
Experience with final clients in an agency our consultancy company role.