LangChain AI/ML Consultant for Generative & MLOps

Ethereum Technologies; Arlington (VA); On-site; USD 90,000 - 128,000; Full time

Job summary

Ethereum Technologies in Arlington, VA is seeking an experienced AI/ML consultant to design and deploy enterprise-grade AI solutions. The role focuses on hands-on development with Python, LangChain, and Generative AI to deliver production-ready applications.

You will build LLM-based systems, RAG pipelines, multi-agent workflows, and tool-calling capabilities, while integrating models with Azure OpenAI, AWS Bedrock, and Hugging Face.

Qualifications

• Strong hands-on experience with Python and AI/ML development.
• Expertise in LangChain, Generative AI and Agentic AI.
• Experience deploying scalable production AI solutions.
• Experience with REST APIs using FastAPI or Flask.
• Familiarity with MLOps and containerization (Docker/Kubernetes).

Responsibilities

• Develop and deploy scalable, production-ready Generative AI applications using Python.
• Build LLM-based solutions using LangChain, LlamaIndex, and Hugging Face.
• Implement RAG pipelines, embeddings, and vector database integrations.
• Develop Agentic AI solutions, multi-agent workflows, and tool-calling capabilities.
• Apply Machine Learning, NLP, and Prompt Engineering techniques.
• Build backend services and REST APIs using FastAPI and Flask.
• Integrate AI models using Azure OpenAI, Azure AI Foundry, and AWS Bedrock.
• Implement LLMOps/MLOps practices for AI deployment and monitoring.
• Containerize and deploy applications using Docker and Kubernetes.
• Work with MCP (Model Context Protocol) for AI tool and system integration.

Skills

Python

LangChain

Generative AI

Agentic AI

ML

NLP

Prompt Engineering

FastAPI

Docker

Kubernetes

Tools

LangChain

LlamaIndex

Hugging Face

Azure OpenAI

Azure AI Foundry

AWS Bedrock

Docker

Kubernetes

FastAPI

Flask

Job description

Ethereum Technologies in Arlington, VA is seeking an experienced AI/ML consultant to design and deploy enterprise-grade AI solutions. The role focuses on hands-on development with Python, LangChain, and Generative AI to deliver production-ready applications.

You will build LLM-based systems, RAG pipelines, multi-agent workflows, and tool-calling capabilities, while integrating models with Azure OpenAI, AWS Bedrock, and Hugging Face.