Senior GenAI Engineer: Enterprise RAG & LLM Orchestration

Morgan Stanley; Newark (NJ); On-site; USD 170,000 - 250,000; Full time

Job summary

Straive is seeking a Senior Generative AI Engineer to design, develop, and deploy production-grade AI solutions. You will architect scalable RAG systems, fine-tune models for domain expertise, and ensure GenAI capabilities integrate into enterprise apps.

You will lead LLM orchestration, optimization, and productization of chatbots and copilots, collaborating across Product, DevOps, and Data teams to elevate production reliability and accuracy.

Responsibilities

• LLM orchestration: design and deploy LLM-based apps.
• Model optimization: fine-tune models for performance and cost.
• RAG systems: architect retrieval-augmented generation pipelines.
• Deployment: containerize services and deploy with FastAPI/Azure Functions.
• Productization: scale enterprise-grade chatbots and copilots.
• Prompt engineering: implement optimization and versioning workflows.
• Monitoring: establish evaluation frameworks to track drift and hallucinations.
• Operationalization: collaborate with cross-functional teams to move POC to production.
• Best practices: set standards for GenAI engineering and ethical safeguards.

Skills

Python

GenAI frameworks

LLM orchestration

Tools

LangChain

LlamaIndex

Semantic Kernel

Pinecone

FAISS

Weaviate

Azure OpenAI

Azure Functions

Azure DevOps

Hugging Face

Job description

Straive is seeking a Senior Generative AI Engineer to design, develop, and deploy production-grade AI solutions. You will architect scalable RAG systems, fine-tune models for domain expertise, and ensure GenAI capabilities integrate into enterprise apps.

You will lead LLM orchestration, optimization, and productization of chatbots and copilots, collaborating across Product, DevOps, and Data teams to elevate production reliability and accuracy.