Role-Agentic AI Engineer
Contract -Long term Contract
Location-Charlotte, NC Hybrid
Key Responsibilities:
- Design, build, and deploy RAG pipelines using vector databases and LLMs (e.g., OpenAI, Mistral, Claude, LLaMA, etc.)
- Develop intelligent AI agents that can reason, plan, retrieve knowledge, and take actions based on goals
- Integrate LLMs with external data sources (e.g., Elasticsearch, Pinecone, Weaviate, LangChain)
- Implement tools for document ingestion, chunking, embedding, and indexing
- Build API services around AI agents for production use
- Fine-tune and evaluate performance of models using feedback loops and A/B testing
- Collaborate with data scientists, ML engineers, and DevOps teams for end-to-end deployment
- Stay current with advancements in RAG, multi-agent systems, and open-source AI frameworks
Required Qualifications:
- Bachelor’s or Master’s degree in Computer Science, AI, ML, or related field
- 3–5+ years of experience in machine learning, NLP, or AI engineering
- Strong programming skills in Python, experience with LangChain, LLamaIndex, or Haystack
- Familiarity with LLMs (e.g., GPT-4, Claude, Mistral, etc.) and embedding models (e.g., OpenAI, Hugging Face)
- Hands-on experience with vector databases (e.g., Pinecone, FAISS, Weaviate)
- Experience developing RAG-based architectures and real-time document retrieval systems
- Proficient in using RESTful APIs, Docker, and Cloud platforms (AWS, GCP, or Azure)
- Solid understanding of NLP concepts: tokenization, embeddings, transformers, prompt engineering
Preferred Qualifications:
- Experience building multi-agent systems or autonomous AI agents
- Knowledge of graph databases, knowledge graphs, or ontologies
- Prior experience in productionizing GenAI products
- Familiarity with LangGraph, AutoGen, CrewAI, or similar agent orchestration frameworks
Contributions to open-source AI/ML projects are a plus