Remote AI/ML Engineer — GenAI, LangChain & RAG Expert

Momento USA LLC; New Jersey; Remote; USD 140,000 - 180,000; Full time

Job summary

Momento USA is seeking an AI/ML Engineer to design and deploy real-world AI/ML systems at scale. You will integrate LangChain and LangGraph to build GenAI apps, implement memory management, and ensure secure, production-ready Python backends using FastAPI.

You will collaborate across teams on embeddings, RAG architectures, LLM integration and monitoring with LangSmith/LangFuse, while leveraging AWS and data pipelines.

Qualifications

• 7+ years in software engineering or applied ML building real-world AI/ML systems; strong Python proficiency and backend development expertise.
• Hands-on experience building GenAI apps with LangChain and LangGraph, including agent design, state/memory management, and graph-based orchestration.
• Proficiency in ML/NLP and generative models; experience with embeddings, vector stores, RAG, and LLM integration/fine-tuning (OpenAI, LLaMA, Cohere, etc.)
• Strong coding in Python and experience with frameworks/tools such as FastAPI, PyTorch/TensorFlow, MLflow; solid understanding of software engineering fundamentals and secure development.
• Experience with AI agent frameworks and MCP; familiarity with agent observability (LangSmith/LangFuse) and agentic RAG patterns
• Track record of delivering scalable, production AI systems and collaborating across teams.
• Experience with agent frameworks (AutoGen, CrewAI), tool-use ecosystems, and advanced planning/reasoning strategies
• Knowledge of cloud platforms (AWS), MLOps, and data pipelines; React.js familiarity is a plus.
• Exposure to enterprise environments and secure, compliant deployments

Skills

Python

Backend APIs (FastAPI)

GenAI apps

LangChain

LangGraph

Embeddings

RAG

LLM integration

MLOps

AWS

Secure development

Agent design

Observability

Tools

PyTorch

TensorFlow

MLflow

LlamaIndex

LangSmith

LangFuse

Job description

Momento USA is seeking an AI/ML Engineer to design and deploy real-world AI/ML systems at scale. You will integrate LangChain and LangGraph to build GenAI apps, implement memory management, and ensure secure, production-ready Python backends using FastAPI.

You will collaborate across teams on embeddings, RAG architectures, LLM integration and monitoring with LangSmith/LangFuse, while leveraging AWS and data pipelines.