Data Scientist (Python, AI/ML)

Data Scientist (Python, AI/ML)

Location Charlotte NC

Client: Wells Fargo

Mode of Interview: In-Person

Job Overview

We are looking for a highly capable Python & AI/ML with deep expertise in backend engineering, LLM-based applications, RAG architectures, and AI agent frameworks.
You will lead the design, development, and deployment of production-grade AI systems built on Python, modern LLM tooling, retrieval engines, embeddings, and vector databases. This is a hands-on leadership role focused on building scalable and intelligent AI products.

Key Responsibilities

• Lead the architecture and development of LLM-driven applications, AI agents, and RAG-based systems.
• Provide technical guidance, conduct code reviews, and mentor junior team members.
• Drive best practices in Python backend engineering, API development, and AI system design.Backend Engineering (Python)

• Build and maintain backend services using FastAPI or Flask.
• Develop scalable API endpoints for AI applications, embeddings, and retrieval systems.
• Ensure backend code quality, modularity, performance, and maintainability.LLMs, RAG, and AI Agent Development

• Build AI applications using: LangChain, LangGraph, Semantic Kernel, Haystack, LlamaIndex, AutoGen
• Develop autonomous or semi-autonomous AI agents with tool calling and workflow graphs.
• Implement Retrieval-Augmented Generation (RAG), embedding pipelines, chunking strategies, reranking, and grounding techniques.
• Work with OpenAI SDK and other LLM providers (Anthropic, Azure OpenAI, Cohere, etc.).
• Manage prompt engineering, prompt routing, safety guardrails, and evaluation metrics.Data & Vector Search Engineering
• Build data pipelines for indexing, embeddings, and retrieval workflows.
• Work with SQL databases (PostgreSQL, MySQL, etc.) for metadata and application storage.
• Work with vector databases such as: Redis, Postgres with pgvector, Elasticsearch, Neo4j, or others.
• Implement and optimize search workflows using FAISS or similar similarity search libraries.

Required Qualifications

• Bachelor s/Master s degree in Computer Science, AI/ML, Data Science, or related fields.
• 10+ years of experience in Python backend development.
• Strong proficiency in FastAPI or Flask.
• Strong working knowledge of SQL databases (Postgres, MySQL, etc.).

Hands-on expertise with vector databases:
Redis, Postgres/pgvector, Elasticsearch, or Neo4j.

• Practical experience with FAISS for similarity search.
• Hands-on experience with modern LLM frameworks:
  LangChain, LangGraph, Semantic Kernel, Haystack, LlamaIndex, AutoGen.
• Strong understanding of:

Embeddings & vector search

RAG pipelines

Retrieval optimization

Chunking strategies

Document loaders & indexing

Experience building AI apps using OpenAI SDK or similar.

Experience deploying APIs/services using Docker and cloud environments.

Leadership experience: guiding teams, conducting reviews, driving architecture decisions