AI Engineer

• Develop and integrate LLM-powered applications and services
• Build and improve RAG pipelines, including document processing, embeddings, retrieval, and generation
• Design and implement AI Agents and agentic workflows
• Integrate tools, function calling, APIs, and external services into AI workflows
• Experiment with different models, prompts, and AI techniques to improve application quality
• Develop and maintain AI services and APIs
• Deploy and monitor AI applications in Linux/Docker environments
• Evaluate model performance, reliability, and response quality
• Troubleshoot and optimize AI applications and inference performance
• Collaborate with software engineers and other teams to deliver production-ready AI solutions

Job Qualification

• Proficiency in Python and experience building AI/ML applications
• Understanding of LLMs, embeddings, RAG, and prompt engineering
• Understanding of AI Agents and agentic workflows
• Familiar with tool calling, function calling, and multi-step AI workflows
• Experience with LLM APIs and AI application frameworks
• Familiar with vector databases such as Milvus, Weaviate, or Chroma
• Basic understanding of LLM inference and deployment
• Familiar with Docker and Linux
• Basic knowledge of REST APIs and databases
• Experience with vLLM, SGLang, or Hugging Face is a plus
• GPU/CUDA and LLM performance optimization knowledge is a plus
• Strong problem-solving and troubleshooting skills