FedEx
Website:
fedex.com
Job details:
Design, develop, and deploy LLM-powered applications for enterprise use cases
Build and optimize RAG pipelines, including:
Vector databases and embeddings
Document ingestion, chunking, indexing, and retrieval strategies
Implement and evaluate fine-tuning approaches (SFT, LoRA, adapters, PEFT techniques)
Work with enterprise LLM platforms ensuring:
Data security, privacy, and compliance
Token efficiency, latency optimization, and cost control
Integrate MCP (Model Context Protocol) or equivalent approaches to manage model context, tool usage, and structured prompts
Develop robust prompt engineering and prompt orchestration strategies
Design scalable APIs and microservices to serve GenAI workloads
Evaluate open-source and commercial LLMs (OpenAI, Azure OpenAI, Anthropic, open-source models, etc.)
Collaborate with MLOps and Platform teams on:
Model monitoring and observability
Versioning, rollback, and lifecycle management
Partner with business and product stakeholders to translate requirements into production-ready GenAI solutions
Click on Apply to know more.