AI Engineer

منذ 24 ساعات

Abu Dhabi Emirate, الإمارات العربية المتحدة AceNet دوام كامل ‏400,000 د.إ.‏ - ‏700,000 د.إ.‏ عقد

Key Responsibilities:

  • Build and integrate AI solutions using OpenAI APIs, Large Language Models (LLMs), and related AI technologies.
  • Develop real-time voice AI and conversational AI applications using Pipecat AI.
  • Design, develop, and implement LLM-based applications, AI agents, chatbots, and conversational interfaces.
  • Build and integrate voice-based AI solutions with LLMs, speech-to-text (STT), and text-to-speech (TTS) services.
  • Develop and integrate REST APIs and backend services to support AI-powered applications.
  • Implement prompt engineering techniques to improve LLM response accuracy, relevance, and overall performance.
  • Integrate AI applications with external APIs, databases, and enterprise backend systems.
  • Explore and implement Retrieval-Augmented Generation (RAG) solutions for context-aware AI applications.
  • Test, troubleshoot, and optimize AI applications for performance, scalability, reliability, and response quality.
  • Independently handle assigned technical development activities, debugging, integration, and deployment.
  • Collaborate with business stakeholders, architects, and development teams to understand requirements and deliver effective AI solutions.
  • Stay updated with emerging AI technologies, LLM frameworks, conversational AI platforms, and industry best practices.

Role Requirements and Qualifications

  • Bachelor's degree or higher in Computer Science, IT, Engineering, or a related field.
  • Minimum 3 years of relevant hands‑on experience in AI/LLM development.
  • Practical hands‑on experience with Pipecat AI for developing real‑time voice AI and conversational applications.
  • Strong understanding of Large Language Models (LLMs) and hands‑on experience integrating OpenAI APIs.
  • Experience developing conversational AI applications, voice assistants, AI agents, and chatbot solutions.
  • Good understanding of REST APIs, backend development, and third‑party API integrations.
  • Experience with prompt engineering and LLM response optimization.
  • Understanding of real‑time communication, voice processing, and conversational workflows.
  • Ability to troubleshoot, debug, and optimize AI‑powered applications.
  • Strong analytical, problem‑solving, and communication skills.
  • Ability to work independently and collaborate effectively with cross‑functional teams.

Preferred Qualifications

  • Experience implementing Retrieval-Augmented Generation (RAG) architectures.
  • Knowledge of vector databases such as Pinecone, FAISS, ChromaDB, or Weaviate.
  • Experience with speech‑to‑text (STT) and text‑to‑speech (TTS) technologies.
  • Familiarity with LangChain, LangGraph, LlamaIndex, or similar LLM frameworks.
  • Experience developing real‑time voice agents and low‑latency conversational AI systems.
  • Knowledge of WebSockets, WebRTC, and real‑time streaming technologies.
  • Experience with cloud platforms such as AWS or Azure.
  • Understanding of AI agent architectures, tool calling, and function calling.
  • Experience with Docker, microservices, and application deployment.
  • Familiarity with Agile/Scrum methodologies.

Why Join Us:

  • Opportunities to work on transformative AI and Generative AI projects with leading global organizations.
  • Continuous investment in learning, upskilling, and professional development.
  • Collaborative work environment with experienced technology professionals.
  • Competitive compensation and comprehensive employee benefits.
  • A culture that encourages innovation, ownership, and career growth.