Senior Full-Stack Software Engineer

Description of the project:

As the Senior Full Stack Software Engineer, you will be the technical lead for a project leveraging the Retrieval Augmented Generation (RAG) approach, where retrieval mechanisms enhance generative AI models by integrating external knowledge sources. You will be responsible for architecting, developing, and deploying scalable AI-driven applications that combine state-of-the-art natural language processing with information retrieval systems. You’ll collaborate closely with business analysts, product managers, and engineers to seamlessly integrate AI models into production environments and optimize the performance of RAG-based systems.

Required skills and experience:

7+ years of full-stack development experience with Python and JavaScript. Proven leadership experience in AI-driven projects or complex software systems is required.
Strong backend development skills in Python and JavaScript, with experience building and maintaining APIs and microservices and working with large-scale data systems.
Expertise in JavaScript and modern frontend development, focusing on delivering responsive and user-friendly applications that integrate complex AI functionalities.
Experience with cloud platforms (AWS, GCP, or Azure) and DevOps practices, including containerization (Docker/Kubernetes) and continuous integration/delivery pipelines.
Strong analytical and critical thinking skills, capable of addressing complex technical challenges related to AI, retrieval, and full-stack integration.
Proven ability to lead a technical team, provide mentorship, conduct code reviews, and ensure high-quality software development practices.
Strong communication skills, with the ability to explain technical concepts to non-technical stakeholders and collaborate across teams.
Professional working proficiency in English

Desirable:

Experience with RAG or similar AI architectures that combine retrieval mechanisms with generative models is desired. Familiarity with information retrieval systems and NLP models is also highly desired.
Understanding machine learning workflows, including model training, deployment, and optimization.
Experience with large language models (LLMs) and knowledge retrieval mechanisms like vector or graph databases.
Experience optimizing the interaction between retrieval systems and generative models to enhance output quality, relevance, and response speed.
Experience with JavaScript (Node.js, VUE.js, and React)
Professional working proficiency in Ukrainian.

Responsibilities:

Leading the development of the RAG-based AI project, overseeing architecture, design, and deployment, defining technical strategy, and guiding the team in best practices.
Building and maintaining robust, scalable applications using Python, Node.js, and React, ensuring the seamless integration of the RAG architecture.
Collaborate with other team members to integrate RAG systems into real-time applications. This includes combining retrieval mechanisms (e.g., search engines or document databases) with generative models to enhance the accuracy and relevance of AI outputs.
Developing efficient backend systems and RESTful APIs to handle high-volume data processing and communication between generative models and retrieval systems.
Leading frontend development using React, designing intuitive user interfaces that allow users to interact with AI models and retrieve relevant data in real-time.
Implement cloud infrastructure and DevOps best practices for deploying scalable AI systems, ensuring RAG components are effectively orchestrated in production environments.
Providing technical guidance, code reviews, and mentorship to junior engineers, fostering a collaborative and high-performing team culture.
Staying informed on the latest advancements in GenAI and full-stack technologies; Proposing and implementing innovative approaches that push the project’s boundaries.

We are delighted to provide you with the following benefits: