AI Engineer
Bellevue, WA - Onsite role
Need VISA INDEPENDENT Only
In order to make an application, simply read through the following job description and make sure to attach relevant documents.
We are seeking a forwardthinking AI Engineer to architect and deploy intelligent systems powered by Large Language Models LLMs RetrievalAugmented Generation RAG and advanced chunking strategies This role is ideal for engineers passionate about building scalable productiongrade AI applications that leverage cuttingedge retrieval and generation techniques
ROLE DESCRIPTION:
Design and implement RAG pipelines using hybrid search vector keyword semantic ranking and metadata enrichment
Apply chunking strategies fixedsize recursive semantic agentic to optimize document segmentation for retrieval and embedding
Finetune and evaluate LLMs eg GPT LLaMA Ollama for tasks such as QA summarization NER and sentiment analysis
Build multiagentic systems
Integrate AI capabilities into enterprise applications using Azure OpenAI Cognitive Search Azure Functions and Power Automate
Collaborate with stakeholders to translate business needs into scalable AI solutions
Ensure model reliability performance and ethical compliance across xsgimln deployments
SKILLS
5 to 7 years of experience as Fullstack developer with at least 24 years in generative AI or RAG systems
Proficiency in
Python
Azure AI Studio Azure Cognitive Services VectorDBs eg Pinecone FAISS
Chunking techniques and embedding strategies
MLOps tools MLflow Docker CICD pipelines