AI Engineer (LLM)

Description

Job Summary: We are seeking a senior technical professional to lead the development of a new LLM-based product, integrating AI into the core service offerings. Key Highlights: 1. Lead the development of a generative AI (LLM) conversational system 2. Design a scalable and secure architecture 3. Implement RAG-based solutions focused on context and accuracy **Description:** Opportunity Responsibilities We seek a senior technical professional with hands-on experience in generative AI and software engineering to lead the development of a new product based on large language models (LLMs), integrating artificial intelligence into Trinks' core services. **Take a look at your role in this \#revolution:** Lead and develop a generative AI (LLM) conversational system; Design a scalable and secure architecture integrated with Trinks' systems; Collaborate closely with Product, UX, Data, and Engineering teams; Implement Retrieval-Augmented Generation (RAG) solutions focused on context and accuracy; Define best practices for AI solution development, versioning, testing, and deployment; Monitor model performance, cost, and security in production. Requirements **What you need for the perfect \#match:** Proven experience in software engineering; Practical experience with LLMs (OpenAI, Claude, Mistral, etc.); Proficiency in Python (C\#/.NET experience is a plus); Knowledge of LangChain, LlamaIndex, or similar frameworks; Cloud architecture expertise (AWS preferred); Familiarity with asynchronous/event-driven systems (Kafka, SQS, etc.). **Nice-to-have skills:** Experience leading or developing generative AI and conversational agent projects. Knowledge of prompt engineering, embeddings, vectors, and light fine-tuning. Experience with hallucination control and safety mechanisms for LLMs. 2512120202501917010