Lead AI Back End Software Engineer (AI Architect Track)

Overview We are looking for a Senior/Lead AI Back End Software Engineer (AI Architect Track) who will drive the architecture and delivery of AI-powered Search solutions, taking ownership of end-to-end system design, model integration, and platform scalability while guiding teams toward production-ready, high-quality outcomes. About Pwrteams Join our fast-growing and diverse team at Pwrteams, where we provide premium IT and engineering nearshore solutions to our global customers. Since 2007, we pursue to become the market leader in assembling cross-border IT and engineering teams for customers. Our operations are strategically positioned within Eastern Europe’s dynamic tech ecosystems, from where we cater the global business landscape.  We’re at the forefront of travel, media and fintech innovation, healthcare efficiency enhancements, and others. Our goal? To connect interesting customer projects and skilled talent alike. Become a part of our team and take the next step on your personal career journey. About The Project TUI, is a global business with over 70 000 people on board, great history and challenging plans for building a digital future. TUI is the largest leisure, travel and tourism company globally, and it owns travel agencies, hotels, airlines, cruise ships and retail shops. You will join a global Search Services team within a large-scale digital platform, responsible for filtering, sorting, and enriching product data for customer-facing systems. The team operates in a highly distributed environment across multiple countries and focuses on building AI-powered search capabilities that enhance user experience through faster, smarter, and more relevant results. Responsibilities Lead the architecture and design of AI-powered Search solutions, covering services, data flows, and model integrationDrive end-to-end delivery from discovery and validation to production and continuous improvementDesign and implement solutions using GenAI models, including orchestration, evaluation strategies, and retrieval-augmented generation (RAG)Define reference architectures and best practices for secure, scalable, and cost-efficient model usageEnsure platform reliability, including latency optimisation, observability, security, and cost controlConduct and guide proof-of-concepts (POCs), validating approaches based on performance, accuracy, and costCollaborate closely with architecture, product, data, and engineering teams to align solutions and trade-offsLead technical discussions, workshops, and design reviews across teamsMentor engineers and contribute to building a strong engineering cultureResearch and promote new technologies, tools, and approaches in AI and backend engineering Qualifications Strong experience designing and operating large-scale backend systems in productionDeep proficiency in Java or Kotlin, with hands-on experience in cloud-native developmentStrong experience with microservices architecture, including performance tuning and reliability patternsExperience with AWS cloud architecture (networking, IAM, observability, scalability)Practical experience delivering AI/LLM-based solutions in production (e.g. RAG, orchestration, evaluation, monitoring)Strong understanding of ML/AI concepts (embeddings, retrieval, model evaluation, safety considerations)Experience with Python and AI/ML toolingExperience with REST and/or GraphQL APIsExperience working with SQL and/or NoSQL databasesStrong DevSecOps mindset and experience with CI/CD pipelinesExcellent communication skills and ability to work with both technical and non-technical stakeholdersLeadership mindset with experience mentoring or coaching engineersHigh level of English (written and spoken)Proactive, ownership-driven, and comfortable working in ambiguous environments Nice to Have Hands-on experience with AWS Bedrock and GenAI toolingExperience with OpenSearch / Elasticsearch and search relevance tuningExperience with Terraform and Infrastructure as CodeFamiliarity with GitLab CI or similar CI/CD toolsExperience defining LLM evaluation frameworks (prompt versioning, testing, red-teaming)Understanding of event-driven architecturesExperience working in global, distributed teams Pwrteams Offers 24 working days of paid vacation11 paid national holidaysHealth care: up to 10 paid sick days, on-demand medical insurance, vaccinationsMental health support: webinars, resources, and compensation for therapy sessionsAccess to our corporate learning platformLanguage classes (English)Flexible benefits budget: a fixed monthly amount you can spend on what matters most to you - medical insurance, sports, leisure, fuel, and more8-hour workday aligned with the client’s working hoursHybrid work options: work from home with the option to use our cozy office space whenever neededEngaging team events and thoughtful gifts throughout the year In your resume please allow our company to use your personal data #PwrteamsCareers