We are looking for a Prompt Engineer to craft, optimize, evaluate, and benchmark prompts for enhanced AI performance at Netomi. This role requires expertise in NLP, AI behavior, and customer-specific business rules. You will collaborate with the Customer Success team and data scientists to develop customized, effective AI solutions.

Role Description We are looking for an experienced and highly knowledgeable Principal/Staff Engineer (Core Product) to join our Engineering team and help drive architecture and technical strategy across our growing suite of core products. The remit and focus of the role is to work across domains on our most complex problems and critical initiatives, helping teams deliver outcomes whilst ensuring architectural excellence. Over time, this role will go where the value is, meaning you should be excited by working across a range of teams and priorities. It’s a broad and exciting role, so we’re looking for someone up for a challenge - if you’re a collaborative and innovative candidate, this is the role for you. Core Responsibilities - Own and deliver clear target architectures, strategies and roadmaps to support our product suite and strategic direction. - Partner with Technical Leads to provide hands-on guidance supporting feature delivery, tech debt paydown, and architecture improvements. - Collaborate with Product Directors to understand product vision and translate this into deliverables, aligning commercial and engineering goals. - Lead our shift to an AI-First way of working, architecting new SDLC foundations and championing the latest approaches to help drive productivity gains across all teams. - Mentor and coach Technical Leads/Senior Engineers on architectural and engineering excellence, continually raising our bar and supporting career growth. - Act as a role model for technical leadership — work with pace, be pragmatic, and stay laser focused on outcomes not output. - Head up architectural reviews for your domain and ensure all designs meet Arbor’s quality, reliability, security and compliance standards. - Collaborate with Staff Engineers and Principal Engineers to shape Arbor’s broader technology strategy, working outside your domain as needed. - Partner with Engineering Management to help grow teams, identify dependencies/risks, and report progress against strategic goals. Qualifications - Extensive track record of delivering outcomes and leading across large, complex product suites, within a scaling and fast-moving environment. - Broad understanding of software architecture, system design, and scalable integration patterns observed from a range of environments. - Examples of communication and influencing across technical and non-technical audiences to achieve positive outcomes. - An ability to support the growth of engineers and technical leads whilst still delivering value across distributed, cross-functional teams. - Demonstrable experience working in an ownership culture where quality, performance, observability, and security are a core responsibility for every engineer. - Deep experience guiding teams in architectural design, de-risking complex initiatives through MVP/0-1 thinking, and framework adoption. - An understanding and opinion on how AI-first engineering will change the SDLC and ways of working, ideally with worked examples. - Examples of contributing to or leading technical communities of practice (e.g. chapters, guilds, architecture councils). - Practical knowledge of and exposure to some of our core stack or equivalent technologies - PHP, Node, React, Python, MySQL, AWS. - Experience navigating between monolithic and distributed architectures with a pragmatic understanding of the value of each. Benefits - The chance to work alongside a team of hard-working, passionate people in a role where you’ll see the impact of your work every day. - A dedicated wellbeing team who champion initiatives such as mindfulness, lunch n learns, manager training, mental health first aid training and much more! - 32 days holiday (plus Bank Holidays). This is made up of 25 days annual leave plus 7 extra company wide days given over Easter, Summer & Christmas. - Life Assurance paid out at 3x annual salary. - Comprehensive wellness benefit provided by AIG Smart Health, which provides a 24/7 virtual GP service, Mental health support, Counselling, and personalised Health Checks. - Private Dental Insurance with Bupa. - Salary sacrifice Pension provided by Scottish Widows. - Enhanced maternity and adoption leave (20 weeks full pay) and paternity (6 weeks full pay) pay. - 5 free return to work maternity coaching sessions, helping you adapt to this new exciting time of life! - Access to services such as Calm and Bippit (financial wellbeing coaching). - All of our roles champion flexible working and we are happy to discuss what this means to you. - Social committees that plan team, office and company wide events to bring people together and celebrate success. - Dedicated professional development training budget (CPD courses, upskilling resources, professional memberships etc). - Volunteer with a charity of your choice for a day each year. - Dog friendly offices! Interview Process - Phone screen - 1st stage - 2nd stage

Role Description Ciklum is looking for a Senior Full Stack Engineer to join our team full-time in Ukraine. As a Senior Full Stack Engineer, become a part of a cross-functional development team engineering experiences of tomorrow. The engineer will work closely with product, architecture, AI engineering, and platform teams to build usable, secure, and scalable agent interfaces that connect into enterprise systems, data sources, LLM services, and internal client platform capabilities. Responsibilities - Build full stack features for AI agent use cases, including chat interfaces, task review screens, approval flows, exception queues and operational dashboards - Develop React/TypeScript frontend components for agent interaction, configuration, monitoring and human-in-the-loop review - Design and implement backend APIs and services that support agent execution, data retrieval, workflow actions, audit trails and enterprise integrations - Connect agents with enterprise systems, databases, document stores, APIs and event-based workflows used within client environment - Integrate with LLM gateways, model platforms, vector stores, prompt/configuration services and AI observability tooling - Implement secure, production-ready patterns for authentication, RBAC, tenant-aware data access, logging, testing, CI/CD and deployment support Qualifications - Strong hands-on experience with React, TypeScript, modern frontend patterns and business application UI development - Backend engineering experience with Python/FastAPI, Java/Spring Boot or Node.js - Experience building REST APIs, integration services and data access layers for enterprise applications - Working knowledge of PostgreSQL or similar relational databases; exposure to vector databases is beneficial - Understanding of AI agent patterns such as tool/function calling, RAG, prompt configuration, workflow orchestration and human-in-the-loop design - Experience with OAuth 2.0, SSO, RBAC, secure API design and multi-tenant application patterns - Familiarity with Git, CI/CD, Docker, Kubernetes, logging and production troubleshooting Requirements - Experience with LangChain, LangGraph, Semantic Kernel, CrewAI, or similar agent frameworks - Exposure to Langfuse, LangSmith, OpenTelemetry, or similar observability tools - Experience with Temporal or workflow orchestration platforms for long-running business processes - Experience building review queues, approval workflows, case management screens, or operational dashboards - Familiarity with AWS services, especially AWS Bedrock, API Gateway, Lambda, S3, and related cloud-native services - Experience working from Figma designs and building reusable UI component libraries Benefits - Strong community: Work alongside top professionals in a friendly, open-door environment - Growth focus: Take on large-scale projects with a global impact and expand your expertise - Tailored learning: Boost your skills with internal events (meetups, conferences, workshops), Udemy access, language courses, and company-paid certifications - Endless opportunities: Explore diverse domains through internal mobility, finding the best fit to gain hands-on experience with cutting-edge technologies - Flexibility: Enjoy radical flexibility – work remotely or from an office, your choice - Care: We’ve got you covered with company-paid medical insurance, mental health support, and financial & legal consultations

Role Description As a Senior Site Reliability Engineer, you will play a pivotal role in managing and owning critical incidents through to resolution to minimize business impact on our key critical business applications and our customer’s business operation and serving as a reliability advisor focused on improving the resilience, observability, and operability of critical platforms and services. - Lead incident response for business-critical services coordinating cross-functional teams and suggest troubleshooting to restore service quickly and minimize business impact. - Proactively notifies internal stakeholders of potential issues impacting service performance; provides regular status updates as required. - Drive blameless postmortems and root cause analysis, turning incidents and recurring issues into systemic fixes, corrective actions, and long-term reliability improvements. - Proactively identify and reduce sources of instability in systems by analyzing how our systems fail in production and driving architectural or operational improvements. - Serve as a senior technical resource and reliability advisor to internal teams, sharing best practices and guiding teams toward sustainable operational excellence. - Partner with engineering/product to shift-left reliability: design/readiness reviews, resilience reviews, and operational acceptance for launches and changes. - Champion culture of reliability across business domains, act as a force multiplier: create clear documentation that enables other teams to adopt reliability improvements at scale. Qualifications - 4-6 years of relevant experience or equivalent combination of education and experience in Senior incident management (with tech focus), SRE, Production Engineering, Software Engineering, DevOps Engineering, or similar role operating business-critical, high-traffic services in production. - Experience with incident management and response: you can navigate ambiguous, high-pressure production issues, drive coordinated response, and follow through with durable improvements. - Track record of proactively identifying reliability risks and gaps through metrics, incidents, architecture reviews, or resilience testing. - Fluent business communication in English (written and spoken). Requirements - Exceptional problem solving, critical systems thinking skills, and familiarity with chaos engineering concepts. - Strong collaboration and influence skills: you communicate clearly, build trust with partner teams, and can guide engineering teams toward better reliability practices. - Growth mindset and curiosity: you are eager to learn, comfortable challenging assumptions (including your own), and motivated by continuous improvement of systems, processes, and yourself. Benefits - Prestige – we are a Key Partner to Financial institutions and Retailers. - Stability & perspective - we have been on the market for many years and operate globally. - Great team - we maintain friendly and helpful relationships, we are not just colleagues. - Future career - you can become a team leader or specialize in your field, grow with us. - Innovation and development - we support individual development and professional training; experienced colleagues are also happy to pass on their experience. - Remuneration - in addition to fair wages, we have annual bonuses according to the company results. - Flexibility - we accommodate parents and support work-life balance. We offer home office including flexible working hours. - Public transport - we will reimburse you for a yearly voucher for Košice MHD / Slovak Bus Lines (AD) / Slovak Railway Transport. - Time off - 5 weeks holiday + 3 sick days. - Equipment - of course you get a laptop and phone including unlimited tariff. - Cafeteria - you choose your own benefits; we will give you generous budget per year to your cafeteria account. - Meal vouchers – you get your meal allowance from day one. - MultiSport - we support the physical and mental health of our colleagues. - The future – we contribute to your pension insurance (III.pilar). - Allowance for working from home – we contribute monthly to your home internet or electricity. - Good thing – we give you 2 days of paid time off for volunteering. - Modern offices – relax zones, video games and great workspace with view on the city.