remoteonsite
LLM Engineer Large Language Models - fospe
LLM Engineer
Lead the design, optimization, and deployment of next‑generation AI products using Anthropic Claude, OpenAI, Gemini, and open‑source LLMs, focusing on AI agents, RAG systems, and enterprise automation.
About the role
Key Responsibilities
- Design, train, and fine‑tune large language models for enterprise‑grade applications.
- Develop and maintain Retrieval‑Augmented Generation (RAG) pipelines to enhance knowledge retrieval and contextual relevance.
- Engineer robust AI agents that automate complex business workflows and integrate with existing systems.
- Implement prompt‑engineering strategies to maximize model performance across diverse use cases.
- Optimize model inference for latency, cost, and scalability on cloud platforms.
- Collaborate with product, data, and DevOps teams to deliver end‑to‑end AI solutions.
Requirements
- Proven experience with LLMs such as Anthropic Claude, OpenAI, Gemini, or comparable open‑source models.
- Strong background in prompt engineering, RAG, and model optimization techniques.
- Hands‑on expertise in Python, PyTorch/TensorFlow, and cloud AI services (AWS, GCP, Azure).
- Solid understanding of AI ethics, bias mitigation, and responsible AI practices.
- Excellent communication skills and ability to translate business needs into technical solutions.
Skills
llmraglangchainpythonawsgcpazurekubernetes