• Design, develop, and maintain the LLM-powered backend services using Python and FastAPI. • Implement retrieval-augmented generation (RAG) to fetch structured and unstructured data from OXRED. • Use frameworks like LangChain, LlamaIndex, or Haystack to manage context retrieval, query routing, and summarization. • Integrate the chatbot logic with the existing OXRED AskOX frontend. • Design, implement, and validate support for diverse fleet analytics use cases including fleet summaries, vehicle diagnostics, predictive insights, and performance metrics. • Ensure secure and efficient data flow between OXRED APIs and the AskOX backend. • Evaluate and improve retrieval accuracy, latency, and hallucination rates. • Maintain technical documentation and API specifications.

Role Description We are looking for a detail-oriented LLM QA Contractor to join an AI validation project focused on improving the quality of Large Language Model (LLM) outputs. You will review photos and delivery instructions, compare them with AI-generated responses, and ensure outputs are accurate, complete, and aligned with established quality guidelines. Your feedback will directly contribute to developing safer and more reliable AI experiences. - Review AI-generated outputs against source images and delivery instructions. - Verify factual accuracy, completeness, and adherence to annotation guidelines. - Identify and classify issues such as hallucinations, missing information, incorrect interpretations, or policy violations. - Provide concise and structured feedback to support continuous model improvement. - Follow detailed Standard Operating Procedures (SOPs) and participate in calibration sessions. - Track your work using annotation tools and spreadsheets. - Escalate ambiguous cases or guideline gaps when needed. - Consistently meet quality, accuracy, and productivity targets. Qualifications - Excellent attention to detail and a structured, analytical mindset. - Previous experience in Content QA, Data Labeling, Trust & Safety, Content Moderation, or similar quality assurance roles. - Strong visual analysis and reading comprehension skills. - Comfortable working with web-based tools, spreadsheets, and annotation platforms. - Reliable, organized, and able to handle repetitive tasks while maintaining a high level of accuracy. - Strong written communication skills in English. - Able to handle confidential and user-generated content responsibly. Requirements - Remote: Work from anywhere. - Contract: Freelance / Service Agreement. - Initial duration: 90-day contract with the possibility of extension. - Schedule: Part-time (4 hours per day). - Weekly workload: The project has two main work peaks each week, on Mondays and Wednesdays. - Critical requirement: Every batch of photos must be reviewed within 36 hours. Meeting this turnaround time is essential. - Availability: No need to work during Portugal business hours. Only 1 hour of overlap is required for a brief team status update on Monday afternoon (Vietnam time) and Wednesday afternoon (Vietnam time). - Rate: USD 11/hour.

Role Description The Conversational AI Engineer is responsible for developing and deploying Conversational AI solutions (chatbots and voicebots), using LLMs, Agentic AI, NLU, and RAG technologies. This role executes technical implementations and integrations across environments while translating business and conversational requirements into scalable, secure, and maintainable technical solutions. It is responsible for defining the technical architecture, integration strategy, APIs, authentication, data flows, AI orchestration, and deployment approach, ensuring compliance with enterprise standards and best practices. The role leads technical discovery and feasibility assessments, implementing and integrating Conversational AI platforms with enterprise systems, CRMs, knowledge bases, telephony, backend services, and third-party applications. It combines expertise in solution architecture, prompt engineering, knowledge base structuring, AI orchestration, and system integration to enable end-to-end automation and continuous improvement. The Conversational AI Engineer also ensures safe and reliable AI model behavior through guardrails, testing, proactive monitoring, troubleshooting, fine-tuning and optimization of prompts, retrieval strategies, and AI model configurations. Additionally, the role oversees STT/TTS configuration and maintenance, voice infrastructure, telephony integration, observability, and performance optimization to guarantee high-quality voice experiences and seamless system integration. Qualifications - Knowledge of Conversational AI, including RAG, LLMs and NLU - Degree or background in engineering or development - Experience working with Conversational AI platforms and deploying AI bots - Experience with speech technologies, including STT (speech-to-text) and TTS (text-to-speech) - Experience in deployment and integration, including APIs and system integrations - Experience with prompt engineering - Ability to clearly document architectures, configurations, and deployment procedures - Fluent in written and spoken English Requirements - Implement, deploy, and maintain Voicebot and Chatbot solutions across development, technical testing/UAT, and production environments - Perform technical discovery and feasibility assessments by evaluating integrations, APIs, data sources, platform capabilities, architecture constraints, technical dependencies, and implementation requirements - Define and maintain the technical solution architecture, including integration architecture, APIs, authentication, data flows, AI orchestration, and deployment approaches, ensuring scalability, security, maintainability, and alignment with enterprise standards - Implement and manage system integrations to enable seamless automation across enterprise platforms, applications, and backend systems - Ensure safe and reliable AI model by implementing safeguards and governance measures - Engineer and refine prompts to guide LLM behavior and ensure precise, context-aware, and business-aligned responses - Structure and optimize knowledge bases to ensure accurate and context-aware responses - Select, configure, integrate, and optimize the most suitable STT and TTS technologies for each use case and language, considering accuracy, latency, voice quality, cost, and platform compatibility to ensure reliable voice performance - Implement and support telephony integrations for voicebot solutions - Apply technical best practices and recommendations for LLMs, Agentic AI, and hybrid AI solutions (NLU + LLM) - Implement new integrations and backend components required to support Conversational AI solutions - Document solution architectures, technical specifications, configurations, integrations, and deployment processes to ensure maintainability and knowledge sharing; Detect and mitigate technical risks and issues - Identify and mitigate technical risks, issues, and dependencies throughout the project lifecycle - Define technical standards, implementation guidelines, and reusable architecture patterns to ensure consistency, scalability, and maintainability across Conversational AI solutions - Collaborate with Conversational Designers, Delivery Managers, Data Analysts, business stakeholders, and cross-functional teams to deliver scalable and business-aligned Conversational AI solutions Benefits - Remote work flexibility - Opportunity to work with leading brands in the CX industry - Access to cutting-edge technology and innovative solutions

• You will own, build, and run your startup in fields such as AI Infrastructure • You will embark on an extensive personal development journey crafted by unicorn founders and follow a fully customised programme enhancing your goal, time, and energy management • You will receive support in hiring through our network to over 50,000 professionals and advice as well as best practices from serial entrepreneurs • You will receive intensive coaching to make your startup ready to raise millions in funding • You will iterate your product with us until having reached product-market-fit and receive support in building up a sales force or creating a marketing engine respectively