AI / LLM Engineer

Company Description

WeCookiT is an international software house that delivers software development to its corporate customers by providing highly skilled, communicative IT professionals to build their customized products through outsourcing, nearshoring and turn-key projects’ solutions.

How do we differentiate ourselves? By investing in the professional growth and personal care of our software developers. We provide them with a premium service so that they can do the same for our customers.

Our talented team holds software engineers and sales experts, spread across offices in Europe and South America, and we represent a go-getting and driven company who aims to be an inspiring software house, knowing our future relies on IT.

WeCookiT stand for growth, support, dynamic, companionship and communication. Our head office is located in Portugal in the heart of Lisbon (Avenida da Liberdade) and we work mainly for the European market.

Job Description

We are looking for an AI Engineer with hands-on experience in Large Language Models (LLMs) to integrate intelligent features into our software product. This role focuses on Java backend development and requires expertise in both cloud and offline/on-premises AI solutions.

Key Responsibilities:

• Integrate LLMs (e.g., GPT-4, Falcon, LLaMA, Mixtral) into Java backend systems.
• Develop local services (in Python or Java) to serve offline models when needed.
• Design and maintain REST/JSON endpoints for communication between Java services and AI modules.
• Personalize and adapt model outputs through prompt engineering.
• Implement logic for natural language understanding, question/answer generation, and response analysis.
• Support hybrid architecture: cloud-first with fallback or dedicated on-premises mode.
• Ensure data privacy, performance, and security in AI integrations.
• Collaborate with backend, frontend (Angular), and product teams for seamless integration.
  
  

Qualifications

Required Skills & Experience:

• Experience with LLMs (e.g., GPT, Falcon, LLaMA, BloomZ).
• Experience integrating APIs (OpenAI, HuggingFace, Ollama).
• Strong Python and Java skills for backend development (FastAPI, Flask).
• Expertise in Java backend development, especially with Spring Boot.
• Familiarity with AWS services (API Gateway, EC2, Lambda, etc.).
• Experience deploying AI models in on-premises environments.
• Familiar with model quantization and serving tools (HuggingFace, llama.cpp, Ollama).
  
  

Nice to Have:

• Familiarity with LangChain, vLLM, or Retrieval-Augmented Generation (RAG).
• Experience with multilingual prompt engineering.
• Working knowledge of Angular.
• Experience with AI solutions in offline enterprise environments.
• Knowledge of privacy regulations (e.g., GDPR) and edge computing best practices.
  
  

Who You Are:

• Solution-oriented, with strong problem-solving skills.
• Comfortable working autonomously and taking technical ownership.
• Eager to collaborate with cross-functional teams.
• Curious and passionate about exploring new AI technologies.
  
  

Additional Information

What We Offer:

• An innovative product focused on real-world Generative AI.
• Influence in technical decisions and solution architecture.
• Flexible, remote work with autonomy.
• Growth opportunities with modern tools and open-source models.
  
  

If you’re excited about making an impact in the AI space, we’d love to hear from you! Apply now and join our dynamic team.