Deskripsi Pekerjaan
Tunas Group is looking for a visionary Staff AI Agent Engineer to join our dynamic technology team in Bandar Lampung. As we pivot towards autonomous business operations, you will be at the forefront of designing, building, and deploying sophisticated AI agent architectures that drive efficiency and innovation across our organizational workflows.
In this role, you will bridge the gap between complex machine learning models and real-world business applications. You will work closely with cross-functional teams to identify automation opportunities, architect robust agentic frameworks, and refine model outputs to achieve measurable operational impact. If you are passionate about LLMs, autonomous problem-solving, and building scalable AI infrastructure, this is the perfect opportunity to shape the future of Tunas Group.
Tanggung Jawab
- Design and develop autonomous AI agents capable of executing complex workflows and decision-making processes.
- Implement and fine-tune Large Language Models (LLMs) and retrieval-augmented generation (RAG) pipelines for business-specific applications.
- Integrate AI agents with internal enterprise systems, APIs, and databases to enable seamless data exchange.
- Conduct continuous monitoring, evaluation, and optimization of AI agent performance, reliability, and security.
- Collaborate with stakeholders to translate business pain points into technical AI-driven solutions.
- Develop robust testing frameworks to ensure accuracy, compliance, and ethical standards in automated processes.
- Stay abreast of the latest advancements in AI research, agentic architectures, and open-source tools to maintain a competitive edge.
Kualifikasi
- Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Robotics, or a related quantitative field.
- Minimum of 3-5 years of professional experience in software engineering, with a strong focus on AI/ML.
- Demonstrated expertise in Python and deep learning frameworks (PyTorch, TensorFlow, or JAX).
- Hands-on experience with LLM orchestration frameworks (LangChain, LlamaIndex, AutoGPT, or similar).
- Solid understanding of vector databases (e.g., Pinecone, Milvus, Chroma) and search-based architectures.
- Familiarity with cloud-native deployment environments (AWS, GCP, or Azure) and containerization tools like Docker and Kubernetes.
- Strong analytical problem-solving skills and the ability to articulate complex technical concepts to non-technical stakeholders.
- Excellent communication skills with the ability to thrive in a collaborative, fast-paced environment.