We are seeking an AI Engineer with strong expertise in open-source LLM fine-tuning, model evaluation, and Retrieval-Augmented Generation (RAG) to build and deploy production-grade AI systems.
Responsibilities
Fine-tune and customize open-source LLMs (e.g., LLaMA, Mistral, Falcon) using techniques such as LoRA, QLoRA, adapters, and full fine-tuning
Design, implement, and optimize RAG pipelines including ingestion, chunking, embedding, retrieval, and re-ranking
Build and maintain evaluation frameworks for LLM performance (accuracy, relevance, hallucination, latency, cost)
Integrate LLMs with structured and unstructured enterprise data sources
Optimize inference performance, cost, and scalability in production environments
Apply security, data privacy, and governance best practices across AI workflows
Requirements
Proven hands-on experience fine-tuning open-source LLMs in real-world applications
Strong experience designing and operating LLM evaluation frameworks
Experience with RAG frameworks (LangChain, LlamaIndex, Haystack, etc.)
Proficiency with vector databases (FAISS, Pinecone, Weaviate, Chroma)
Strong Python skills and experience with APIs and cloud platforms (AWS/GCP/Azure)
Experience deploying and monitoring AI systems in production
Contact us:
Job ID: LSIT/HY/AIEL/02/26
Tel: 040-29347004
E-Mail: careers@logisofttechinc.com