FULL STACK AI ENGINEER

Apply Now FULL STACK AI ENGINEER Apply Now COUNTRY Colombia FORMAT Remote Svitla Systems Inc. is looking for a Full Stack AI Engineer for a full-time position (40 hours per week) in Colombia. Our client is a leading provider of hospitality technology solutions, empowering hotels worldwide to drive revenue, enhance guest experiences, and optimize operations. The integrated platform combines CRM, email marketing, business intelligence, and eCommerce solutions purpose-built for the hospitality industry. You will design, build, and deploy intelligent features that transform the hospitality technology products. You will own the complete implementation lifecycle—from infrastructure and data pipelines to backend AI integration and responsive user interfaces—delivering production-ready AI capabilities that create measurable value for our customers. Working across the polyglot technology stack (.NET, Node.js, Python), you will integrate large language models, implement retrieval-augmented generation (RAG) systems, and build scalable AI-powered APIs. As part of our AI Power Team initiative, you will operate with significant autonomy, driving AI adoption across the product portfolio while establishing best practices for enterprise AI development in the hospitality technology space. Key Technologies & Tools: Languages: Python, JavaScript/TypeScript, C#/.NET, SQL; Frontend: React, Vue.js, Angular, HTML/CSS, modern JavaScript tooling; Backend: .NET/C#, Node.js, Express, ASP.NET, Python frameworks (FastAPI, Flask); AI/ML: OpenAI, Anthropic Claude, Azure OpenAI, LangChain, LlamaIndex, vector databases (Pinecone, Weaviate, pgvector); Databases: SQL Server, PostgreSQL, MongoDB, Redis; Cloud & DevOps: AWS/Azure/GCP, Docker, Kubernetes, CI/CD pipelines, Git; Monitoring: application monitoring, logging frameworks, observability platforms. REQUIREMENTS 3+ years of experience in software development with production systems 1+ years of hands-on experience building AI-powered features or integrating LLMs into production applications. Bachelor's degree in Computer Science, Software Engineering, or related technical field (or equivalent practical experience). Demonstrated ability to work independently on complex technical projects with minimal oversight. Strong knowledge of at least 2 of the following languages: Python, JavaScript/TypeScript, C#/.NET, with the ability to work across the stack. Experience with modern frontend frameworks React, Vue.js, Angular, building responsive, performant user interfaces. Expertise in backend development including RESTful API design, microservices architecture, and database operations (SQL and NoSQL). Solid understanding of software engineering fundamentals: data structures, algorithms, design patterns, testing methodologies. Practical experience with LLM APIs (OpenAI, Anthropic, Azure OpenAI) including prompt engineering and output evaluation. Understanding of RAG architectures and experience with vector databases (Pinecone, Weaviate, Chroma, pgvector). Familiarity with AI orchestration frameworks (LangChain, LlamaIndex, Semantic Kernel) and their practical application Knowledge of embedding models, similarity search, and context window management for LLM applications. Experience deploying applications to cloud platforms (AWS, Azure, or GCP) and managing cloud resources. Practical understanding of containerization (Docker) and orchestration (Kubernetes) for deploying scalable services. Understanding of CI/CD pipelines, automated testing, and deployment automation practices. Ability to identify performance bottlenecks in distributed systems and implement optimization strategies. Basic understanding of system monitoring, logging, and observability tools (CloudWatch, Datadog, New Relic, or similar). Strong problem-solving skills with a systematic approach to debugging complex technical issues. Excellent communication skills with the ability to explain technical concepts to diverse audiences. Self-directed work style with proven ability to manage multiple priorities and deliver results independently. Collaborative mindset with experience working in cross-functional teams. Continuous learning orientation with curiosity about emerging AI technologies and industry developments. NICE TO HAVE Master's degree in Computer Science, AI/ML, or related field. Experience in hospitality technology, SaaS platforms, or CRM/marketing automation systems. Background in machine learning fundamentals (model evaluation, training pipelines, feature engineering) Familiarity with data engineering concepts (ETL processes, data warehousing, stream processing). Experience with infrastructure-as-code tools (Terraform, CloudFormation, Pulumi). Knowledge of AI safety, responsible AI practices, and prompt injection prevention techniques. Contributions to open-source projects or technical writing demonstrating AI/ML expertise. Familiarity with A/B testing, feature flags, and gradual rollout strategies for production features. Understanding of SQL Server, PostgreSQL, MongoDB, and other database technologies. RESPONSIBILITIES Design and implement end-to-end AI features using LLMs (OpenAI, Anthropic, Azure OpenAI) integrated into existing products across hospitality workflows. Build and optimize RAG (Retrieval-Augmented Generation) systems using vector databases (Pinecone, Weaviate, pgvector) to ground AI responses in proprietary data. Develop prompt engineering strategies and implement systematic evaluation frameworks to ensure AI outputs are high-quality, reliable, and aligned with business goals. Create intelligent APIs and microservices that expose AI capabilities to internal teams and external integrations, implementing proper rate limiting, error handling, and monitoring. Build responsive user interfaces using modern frameworks (React, Vue.js, Angular) that surface AI capabilities through intuitive, performant experiences. Develop backend services across the technology stack (.NET/C#, Node.js, Python), implementing business logic, data processing, and AI orchestration workflows. Design and maintain data pipelines that prepare, transform, and serve data to AI systems, ensuring data quality and system reliability. Write clean, testable, maintainable code following established development standards and best practices across all layers of the application stack. Stand up cloud infrastructure (AWS, Azure, GCP) for AI workloads, including compute, storage, networking, and security components. Implement CI/CD pipelines for AI-powered applications using containerization (Docker, Kubernetes) and infrastructure-as-code practices. Monitor system performance, identify bottlenecks in AI inference pipelines, and optimize for latency, throughput, and cost efficiency. Establish observability practices for AI systems, including logging, metrics, tracing, and alerting, to ensure production reliability. Operate independently on AI initiatives with minimal guidance, owning projects from concept through deployment and ongoing operational support. Collaborate with product managers, designers, and stakeholders to translate business requirements into technical AI solutions and realistic implementation plans. Contribute to the AI Power Team initiative by establishing best practices, documenting patterns, and mentoring team members on AI integration techniques. Conduct code reviews, participate in architectural discussions, and drive continuous improvement of development processes and technical standards. Stay current with AI/ML technologies, frameworks, and industry trends, evaluating new tools and approaches for applicability to products. Provide on-call production support as needed, troubleshooting issues and implementing fixes across the full application stack. WORKING CONDITIONS Primarily remote or hybrid work arrangement with flexibility for distributed collaboration; Standard work hours with occasional evening/weekend work for deployments or critical production issues; Participation in on-call rotation for production support as needed; Fast-paced environment with multiple concurrent projects and evolving priorities; Collaborative culture with emphasis on knowledge sharing and continuous learning. WE OFFER US and EU projects based on advanced technologies. Competitive compensation based on skills and experience. Annual performance appraisals. Remote-friendly culture and no micromanagement. Comprehensive private medical insurance. Christmas Bonus in the amount of 50% of the monthly payment. Bonuses for article writing, public talks, other activities. 15 vacation days, 10 holidays, 10 sick leaves. Personalized learning program tailored to your interests and skill development. Free tech webinars and meetups organized by Svitla. Fun corporate online\offline celebrations and activities. Awesome team, friendly and supportive community! ABOUT SVITLA Svitla Systems is a global digital solutions company headquartered in the U.S. and operating across the Americas, Europe, Asia, and APAC. Since 2003, we have served a wide range of clients — from innovative start-ups to Fortune 500 companies. Our success is built on partnership. By integrating seamlessly with clients’ teams, we create lasting collaborations that drive real results. We are strong advocates of workplace flexibility, remote culture, individual approach to professional and personal growth. Svitla is proud to be an equal opportunity employer. All qualified applicants will receive consideration for cooperation without regard to age, gender identity, sexual orientation, religion, race, color, national origin, disability, or any other characteristic protected by applicable law. Our global mission is to build a business that contributes to wellbeing of our partners, personnel, and their families, improves our communities, and makes a lasting difference in the world. Together, we are coding a brighter tomorrow — and living it. Join us! LET'S MEET IN PERSON Anastasia Tkachenko RECRUITER Email: a.tkachenko@svitla.com LinkedIn: Anastasia Tkachenko