AI Prompt Engineer (technical engineering)

In this role you design and optimize prompts and build scalable GenAI workflows that connect people with intelligent systems. You will work across prompting, reasoning systems, and GenAI application engineering to integrate LLMs into production-grade solutions. The position emphasizes building high-performance pipelines, tool-enabled workflows, and observability to advance cutting-edge AI capabilities. You will collaborate with cross-functional teams to shape scalable GenAI solutions and stay ahead of rapid advancements in the field. This opportunity offers hands-on work with leading models and a focus on real-world impact.

• Design, test and optimize prompts for frontier models
• Build agentic workflows with tool calls, memory, retrieval pipelines and structured reasoning
• Integrate LLMs into applications using LangChain, LlamaIndex, Haystack, AutoGen and OpenAI patterns
• Develop high-performance RAG pipelines with embedding optimization and evaluation harnesses
• Deploy scalable APIs, microservices and serverless workflows
• Containerize and deploy workloads, optimize performance with quantization, distillation, caching, batching and routing

• Strong Python skills
• Experience with Transformers, LangChain, LlamaIndex
• Knowledge of vector databases (FAISS, Pinecone, Milvus, Weaviate, ChromaDB)
• Hands-on Linux, Bash/Powershell, containers and cloud environments
• Good communication, creativity and systems-thinking mindset
• Curiosity and adaptability to GenAI pace

• strong communication
• creativity
• systems-thinking
• Transformers
• LangChain
• LlamaIndex