AI Engineer Intern

Emplay; United States; Remote; USD 120,000 - 170,000; Full time

Job summary

Emplay is hiring for a remote backend AI engineer to design and build LLM-powered agents and scalable backend services. You will architect end-to-end RAG pipelines and integrate with enterprise platforms via APIs and webhooks.

The role involves developing bulk data pipelines, analytics, and secure APIs, using AWS services and modern authentication standards such as OAuth 2.0, SAML, and OIDC. Collaborative work with product and engineering teams is expected.

Qualifications

• 2–3 years of backend/AI experience.

Responsibilities

• Designing and building LLM-powered agents alongside scalable backend services.
• Architecting and optimizing end-to-end RAG pipelines.
• Working with MCP and multi-agent workflows.
• Building integrations with enterprise platforms through APIs and webhooks.
• Developing bulk data pipelines and usage analytics.
• Working across AWS services including Lambda, ECS/EKS, S3, DynamoDB, OpenSearch and SQS.
• Building secure, production-grade APIs and services.
• Working with authentication and identity standards including OAuth 2.0, SAML and OIDC.
• Delivering scalable AI and backend solutions in collaboration with product and engineering teams.

Skills

Python

REST APIs

GraphQL

FastAPI / Flask

OAuth 2.0 / SAML / OIDC

Tools

AWS Bedrock

OpenAI/Anthropic models

LangChain / LlamaIndex

MCP and multi-agent systems

Terraform / AWS CDK

OpenSearch / Pinecone / pgvector

REST & GraphQL APIs

AWS services (Lambda, ECS/EKS, S3, DynamoDB, SQS)

Job description

Batch: 2026,2027. About the role:

• This is a remote, work from home position for a candidate with 2 to 3 years of experience.
• The role sits within a team building scalable AI-powered backend systems and enterprise integrations.

What you'll work on:

• Designing and building LLM-powered agents alongside scalable backend services.
• Architecting and optimizing end-to-end RAG pipelines.
• Working with MCP and multi-agent workflows.
• Building integrations with enterprise platforms through APIs and webhooks.
• Developing bulk data pipelines and usage analytics.
• Working across AWS services including Lambda, ECS or EKS, S3, DynamoDB, OpenSearch and SQS.
• Building secure, production-grade APIs and services.
• Working with authentication and identity standards including OAuth 2.0, SAML and OIDC.
• Delivering scalable AI and backend solutions in collaboration with product and engineering teams.

What we're looking for:

• Experience with AWS Bedrock and models from providers such as OpenAI or Anthropic.
• Advanced knowledge of RAG techniques and vector databases such as OpenSearch, Pinecone or pgvector.
• Experience with LangChain or LlamaIndex, MCP and multi-agent systems.
• Strong Python skills along with FastAPI or Flask.
• Familiarity with REST and GraphQL APIs.
• Knowledge of OAuth 2.0, SAML and OIDC.
• Experience with infrastructure as code tools such as Terraform or AWS CDK.