Senior LLM Engineer

Company DescriptionPT Bukit Teknologi Digital (BTECH), established in 2023, is a member of BUMA International Group.BTECH provides end to end mining technology solutions, including Asset Management, SHE, and People Management, as well as Mine Engineering. The company focuses on delivering operational and financial efficiency, scalability, and sustainability for mining organizations through machine learning capabilities and cutting edge technologies. BTECH combines advanced technologies and world class mining practices to add value and achieve the business objectives of our clients.Job Descriptions:Design, finetune, and evaluate Large Language Models (LLMs) such as GPT, LLaMA, Claude, and Mistral for enterprise-grade or domain-specific applications.Develop custom model architectures, advanced embedding strategies, and robust prompt-engineering frameworks.Implement model-optimization techniques, including model compression, retrieval-augmented generation (RAG), and multi-agent orchestration.Build scalable training, evaluation, and deployment pipelines for LLM-based applications across cloud and on-premise environments.Integrate LLMs with APIs, enterprise systems, relational databases, NoSQL stores, and knowledge repositories.Collaborate closely with Data Engineers, ML Engineers, Product Managers, and domain experts to translate business challenges into end-to-end AI solutions.Experiment with advanced grounding, alignment, and model-interpretability techniques to ensure reliability and factual consistency.Design and implement knowledge-centric architectures by leveraging knowledge graphs, graph databases, and entity-relation modeling to enhance model reasoning and contextual accuracy.Prototype and enhance “Modified AI” capabilities, such as custom reasoning modules, AI agent behaviors, or domain-adaptive model components.Qualifications:Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a related field.Strong proficiency in Python and ML frameworks such as PyTorch, TensorFlow, Hugging Face Transformers, LangChain, or LlamaIndex.Deep understanding of LLM architectures, tokenization, embeddings, attention mechanisms, and various finetuning strategies (LoRA, PEFT, full finetuning, etc.).Experience with vector databases such as Pinecone, Milvus, or FAISS and hands-on implementation of end-to-end RAG pipelines.Proven experience implementing Graph Databases (e.g., Neo4j, TigerGraph, ArangoDB) and integrating knowledge graphs into AI or LLM systems.Practical experience in developing or modifying AI systems (“Modify AI”), including customizing model logic, agent behavior, reasoning modules, or domain-specific adaptation layers.Strong understanding of NLP, information retrieval, entity-linking/NER, and knowledge-graph-based reasoning is a strong advantage.Experience with cloud-based AI platforms (AWS Sagemaker, Azure OpenAI, GCP Vertex AI, etc.) and distributed training environments.Strong problem-solving skills, analytical thinking, and the ability to work in cross-functional teams within fast-paced environments.