Production-Grade AI Engineer Intern

Spatium Lab LLC; Bellevue (WA); Presencial; USD 83 000 - 152 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Direct mentorship from founders

Ownership of production projects

Resumo da oferta

Spatium Lab LLC is seeking an experienced AI engineer to build production-grade features for B2B SaaS. You will design RAG pipelines, enable function calling with reliable execution, and integrate LLMs across AWS Bedrock, GCP Vertex AI, or OpenAI APIs.

You'll develop MCP servers and A2A workflows, ensure data isolation in multi-tenant environments, and handle async processing with Celery or SQS. A hands-on portfolio is valued for this role as production impact is immediate.

Qualificações

• Strong Python skills with async programming experience.
• Understanding of transformer architectures and LLM fundamentals—how they work, not just how to call them.
• Experience building with LangChain, LlamaIndex, or similar orchestration frameworks.
• Knowledge of vector databases (Pinecone, Weaviate, Chroma, pgvector).
• Familiarity with AWS or GCP cloud services and containerization (Docker).
• Understanding of security principles for multi-tenant systems—data isolation matters.
• Experience with message queues and background processing (Celery, SQS, Redis).
• Self-directed problem solver who designs solutions, not just implements specs.
• Proficiency with AI coding tools and prompt engineering—hands-on projects.

Responsabilidades

• Design and implement RAG pipelines for engineering documentation and knowledge bases.
• Build function/tool calling systems with structured outputs and reliable execution.
• Integrate LLMs via AWS Bedrock, GCP Vertex AI, or OpenAI APIs.
• Develop MCP servers and A2A workflows for production use.
• Implement secure, multi-tenant AI features that protect data isolation.
• Build background task pipelines (Celery, SQS) for async AI processing at scale.
• Create embeddings pipelines and manage vector databases for semantic search.
• Monitor AI system performance, costs, and quality metrics in production.

Conhecimentos

Python async

Transformer architectures

LangChain

Vector databases

AWS/GCP cloud

Security multi-tenant

Background processing

AI tooling / prompts

Problem solving

Self-directed

Ferramentas

LangChain

LlamaIndex

Pinecone

Weaviate

Chroma

pgvector

Docker

SQS

Descrição da oferta de emprego

Spatium Lab LLC is seeking an experienced AI engineer to build production-grade features for B2B SaaS. You will design RAG pipelines, enable function calling with reliable execution, and integrate LLMs across AWS Bedrock, GCP Vertex AI, or OpenAI APIs.

You'll develop MCP servers and A2A workflows, ensure data isolation in multi-tenant environments, and handle async processing with Celery or SQS. A hands-on portfolio is valued for this role as production impact is immediate.