PS
AI Specialist
Accepting applicationsPrestige Staffing · Charlotte, NC
Full-Time Mid_senior AIPythonaIaiate
Posted
4d ago
Category
Test
Experience
Mid_senior
Country
United States
Our client is looking for a Senior Python / AI Engineer to help build and deploy production-grade AI applications that integrate large language models with enterprise data. This role is hands-on and engineering-focused, centered on delivering reliable, scalable AI services rather than research or experimentation.
You’ll work on end-to-end solutions that include Python-based APIs, retrieval-augmented generation (RAG) pipelines, agent-style workflows, and cloud deployments. The ideal candidate is comfortable owning backend architecture, translating business needs into technical solutions, and operating in a mature, enterprise environment.
What You’ll Be Doing
Design and develop Python services that integrate LLMs with structured and unstructured data
Build and maintain RAG pipelines using embeddings and vector databases
Implement agent-style workflows using frameworks such as LangChain or LlamaIndex
Develop and expose APIs that connect data sources, tools, and model endpoints
Prepare and structure data for AI use cases (SQL, document parsing, metadata tagging)
Deploy and operate AI services in AWS using Docker and cloud-native patterns
Evaluate model performance, prompts, and retrieval quality; support lightweight fine-tuning when needed
Collaborate with internal teams to deliver scalable, production-ready solutions
What We’re Looking For
3+ years of professional Python development experience
Hands-on experience building and deploying AI or data-driven applications
Practical experience with LLMs, embeddings, and retrieval-augmented generation (RAG)
Familiarity with vector databases (e.g., Pinecone, FAISS, Weaviate, Chroma)
Experience building APIs and backend services
AWS and Docker experience in production environments
Strong software engineering fundamentals and a production-first mindset
Nice to have
Experience with agent frameworks or multi-agent orchestration
Exposure to model evaluation, prompt testing, or lightweight fine-tuning approaches
Background working in large enterprise or regulated environments
Show more Show less
You’ll work on end-to-end solutions that include Python-based APIs, retrieval-augmented generation (RAG) pipelines, agent-style workflows, and cloud deployments. The ideal candidate is comfortable owning backend architecture, translating business needs into technical solutions, and operating in a mature, enterprise environment.
What You’ll Be Doing
Design and develop Python services that integrate LLMs with structured and unstructured data
Build and maintain RAG pipelines using embeddings and vector databases
Implement agent-style workflows using frameworks such as LangChain or LlamaIndex
Develop and expose APIs that connect data sources, tools, and model endpoints
Prepare and structure data for AI use cases (SQL, document parsing, metadata tagging)
Deploy and operate AI services in AWS using Docker and cloud-native patterns
Evaluate model performance, prompts, and retrieval quality; support lightweight fine-tuning when needed
Collaborate with internal teams to deliver scalable, production-ready solutions
What We’re Looking For
3+ years of professional Python development experience
Hands-on experience building and deploying AI or data-driven applications
Practical experience with LLMs, embeddings, and retrieval-augmented generation (RAG)
Familiarity with vector databases (e.g., Pinecone, FAISS, Weaviate, Chroma)
Experience building APIs and backend services
AWS and Docker experience in production environments
Strong software engineering fundamentals and a production-first mindset
Nice to have
Experience with agent frameworks or multi-agent orchestration
Exposure to model evaluation, prompt testing, or lightweight fine-tuning approaches
Background working in large enterprise or regulated environments
Show more Show less