Senior Engineer AI Specialist

At Mindera, we believe that software is built by people, for people, with high-performance systems that impact users worldwide.

As a Senior AI Engineer you'll be part of the development of our next-generation autonomous AI agents and intelligent workflows. In this role, you will design, build, and deploy production-grade agentic architectures, bridging advanced LLM reasoning with existing enterprise backends. You will be instrumental in building Model Context Protocol (MCP) servers, crafting custom sub-agent ecosystems, and integrating advanced RAG and memory pipelines into robust Java-based applications.

We value empathy, self-organization, and a positive attitude. If you are approachable, communicate clearly, and believe that team fit is just as important as technical expertise, you'll feel right at home here.

At Mindera, we encourage the use of AI to assist with coding and related tasks. We find that a person's engineering and software craft skills have a big impact on long-term successful delivery, with or without AI. Our goal in the interview process is to understand the candidate’s knowledge and skills in engineering. If you need to, or plan to use AI, please be transparent with us when you're using it, to avoid issues and misunderstandings that can either impact your chance of securing the role or impact your success at Mindera.

When you join Mindera we welcome you into a fun and politics-free work culture , built on the principles of lean and self-organisation.

Note: Depending on the project and our clients' needs, you may get the chance to pack your bags and take off every now and then. Typically, we estimate travel time to be between 0% and 15%.

At Mindera, we thrive on solving complex engineering challenges and driving technological innovation. As a Senior Engineer AI Specialist , you will focus on:

• Backend & AI Integration: Build scalable microservices using Java 17/21+ and Spring Boot, integrating commercial LLMs (e.g., Azure OpenAI Service, Anthropic Claude, OpenAI) via Spring AI.
• Agentic Systems: Architect autonomous, multi-agent workflows using one or more of LangGraph, LangChain4j, or CrewAI, for dynamic, multi-step reasoning.
• Context & Memory: Develop MCP (Model Context Protocol) servers, work with vector databases, and build RAG pipelines for efficient, persistent data retrieval.
• Prompting & Skills: Create and version-control custom AI "skills" and complex prompts (e.g., using .md files) for safe, deterministic outputs.
• Enterprise Reliability: Implement AI guardrails, rate limiting, fallbacks, and observability/tracing for secure, production-grade performance.
• Collaboration: Partner with App Engineers, Product, and Data teams to deliver seamless end-to-end AI experiences on Mobile and Web.

Requirements

Key Qualifications:

• Experience: 7+ years of professional software engineering experience (BSc in Computer Science or a related field, or equivalent experience).
• Backend Mastery: Strong, hands-on proficiency with Java 17/21+ and Spring Boot in production environments.
• AI Integration: Proven experience integrating commercial LLMs into enterprise logic, ideally using Spring AI.
• Agentic Frameworks: Practical, recent experience building autonomous or multi-agent systems using at least one of LangGraph, LangChain4j, or CrewAI.
• Context & Memory: Solid conceptual and hands-on grounding in RAG pipelines, vector databases, and MCP (Model Context Protocol) - given how young these technologies are, we're looking for depth of understanding and the ability to build with them, not years of tenure on any single tool.
• AI Tooling: Ability to create discrete AI "skills", sub-agents, and robust prompts for multi-step reasoning.
• Documentation: Clear technical writing skills for APIs, system architecture, and developer guides.
• AI Ecosystem & Adaptability: Proactively staying up to date with rapid changes and latest releases in the AI ecosystem, with a track record of adapting tools and practices accordingly.

Nice-to-Have:

• AI Evaluation: Background in tracing and evaluation frameworks (e.g., LangSmith, Ragas, TruLens, Langfuse).
• Local Models: Familiarity with deploying and fine-tuning local models (e.g., Ollama, vLLM).
• Python: Proficiency for rapid AI prototyping and experimentation alongside Java.

Benefits

THE PERKS OF BECOMING A MINDER:

• Private medical subscription
• Private medical subscription for children
• Counseling and psychotherapy services
• Reimbursement for eyeglasses
• Self-proposal salary process
• Annual profit distribution, subject to company performance and board decision
• Mindera Unit Plan
• Flexible benefits options (sports, medical, cultural, donations)
• Trainings and learning opportunities to grow within your role
• Coaching and development guidance
• 25 days holiday
• Flexibility to choose where you work from
• Vacation incentive
• Parties, gatherings & trips

WHY MINDERA?

We're thrilled to have the opportunity to share with you what it's like to be a part of the Mindera community.

We're a group of friendly and talented individuals who work together to bring projects to life, in a fun, politics-free environment.

Our culture is all about being adaptable and self-organized. We want Minders to take risks, make decisions, work together and feel free to be their most authentic selves, every single day.

We work closely with our clients to truly understand their products and develop high-performance, resilient, and scalable software systems that make a real impact for their users and businesses, worldwide.

We are proud of our work, we're always learning and growing in our Agile and collaborative environment, and we hope you'll love it here just as much as we do!

Check out our Handbook & get to know us better:

Mindera around the world: Porto, Portugal | Aveiro, Portugal | Coimbra, Portugal | Leicester, UK | San Diego, USA | San Francisco, USA | Chennai, India | Bengaluru, India | Blumenau, Brazil | Cluj-Napoca, Romania | Valencia, Spain | Casablanca, Morocco | Melbourne, Victoria, Australia & Remote