Senior Generative AI Engineer

This is a fully remote position, open to applicants in Portugal.

📋 Description

• Design, develop, and maintain scalable backend services for applications powered by AI.

• Create and implement production-ready Generative AI solutions utilizing Large Language Models (LLMs).

• Design, optimize, and evaluate Retrieval-Augmented Generation (RAG) and tool-based pipelines, as well as AI orchestration workflows, which include chunking strategies, hybrid retrieval, reranking, and retrieval quality assessment.

• Develop scalable APIs, distributed systems, and vector search solutions.

• Assess, integrate, and optimize foundation models for various use cases.

• Enhance AI systems for improved performance, scalability, and reliability.

• Work collaboratively with cross-functional teams to establish technical solutions and facilitate product evolution.

• Contribute to software architecture, technical documentation, and engineering best practices.

• Investigate and assess emerging AI technologies.

• Lead design reviews, set engineering standards, and mentor engineers on best practices for Generative AI.

⛳️ Requirements

• A degree in Computer Science, Software Engineering, or a related discipline.

• Over 5 years of professional experience in software development.

• More than 2 years of practical experience in designing and building Generative AI applications using Large Language Models (LLMs).

• Direct experience with speech and multimodal models, including speech-to-text (STT), text-to-speech (TTS), speech-to-speech, and vision-capable LLMs that handle image processing.

• Proficiency in utilizing and developing applications on these models, encompassing real-time (streaming) and Completions/Responses APIs, tool invocation, model deployment, and model assessment.

• Significant experience with scalable backend systems and distributed architectures.

• Strong expertise in Python, particularly in asynchronous and concurrent programming for I/O-bound LLM workloads.

• Solid grasp of software engineering best practices, including design patterns, testing methodologies, and CI/CD.

• Familiarity with RESTful APIs, microservices, and event-driven architectures.

• Experience in developing production-ready AI applications.

• Knowledge in defining and applying structured evaluation methodologies for LLM and RAG systems, such as retrieval and generation quality metrics.

• Awareness of cloud-native architectures, containerization, and orchestration technologies.

• Understanding of responsible AI and security protocols, covering data privacy, prompt-injection defense, and safe model output handling.

• Strong analytical, problem-solving, and communication abilities.

• Above all, a strong product intuition and a keen sense for user experience, adept at creating AI solutions that are intuitive and reliable for end-users.

• Proficient in English.

🏝️ Benefits

• Competitive compensation package

• Environment that promotes personal and professional growth