GenAI/LLM Engineer
Core
Design and build production-ready generative AI applications for enterprise search, summarization, and content generation using large language models.
Role type
Senior IC GenAI/LLM Engineer
Builds
Scalable LLM application architectures and AI-powered software systems
Domain
Generative AI, Natural Language Processing, Enterprise Software
Deliverable
production ML models
Required skills
Python, Prompt Engineering, Parameter-efficient fine-tuning (PEFT/LoRA), Transformer architectures, REST API development, Vector search/embeddings, LLM evaluation frameworks
Preferred skills
Experience with LangChain, LlamaIndex, Semantic Kernel, FastAPI, Flask, GPT-4, Claude, Llama 3, Mistral
Technologies
LangChain, LlamaIndex, Semantic Kernel, FastAPI, Flask, GPT-4, Claude, Llama 3, Mistral, PEFT, LoRA
Responsibilities
Design high-performance GenAI apps; Develop and refine prompt templates; Prepare custom datasets and implement fine-tuning; Integrate LLMs into backend microservices; Optimize inference costs and latency; Work with embedding models and vector indexes; Establish automated LLM evaluation suites
Seniority
Mid-senior, hands-on IC