Offer summary

Qualifications:

Over 8 years of software engineering experience with a focus on AI and LLMs., Strong expertise in deploying, prompt engineering, and managing context in LLM systems., Proficiency with vector databases like Pinecone, Weaviate, or Milvus, and experience with RAG pipelines., Experience designing context-aware, memory-augmented AI systems and familiarity with agent orchestration frameworks..

Key responsibilities:

Design and develop the Model Context Protocol (MCP) for managing AI context and memory.

Manage real-time context orchestration and conversation states across multiple AI agents.

Fine-tune, deploy, and manage LLMs for commerce-related applications.

Collaborate with cross-functional teams to integrate AI solutions and ensure security and compliance.

Job description

We’re looking for a Principal AI / LLM Engineer to lead the development of our Model Context Protocol (MCP)—a system for managing context, memory, and dynamic orchestration of LLM workflows across the Emcee ecosystem.

What You'll Do

AI & LLM Architecture (MCP-Focused)

Design and build the Model Context Protocol (MCP):
- Manage real-time context orchestration, memory systems, and conversation state across multiple AI agents and use cases.
- Handle context injection, summarization, and retrieval pipelines for LLM workflows.
Develop LLM-powered commerce experiences including personalized shopping flows, creator support agents, and dynamic product recommendations.

LLM Deployment & Integration

Fine-tune, deploy, and manage LLMs (OpenAI, Anthropic, open-source models like Llama/Mistral) for commerce-specific tasks.
Build retrieval-augmented generation (RAG) pipelines using embeddings and vector databases to enhance LLM outputs with up-to-date brand, product, and user data.

Cloud & Infrastructure Engineering

Architect event-driven AI pipelines using AWS (Lambda, EventBridge, SQS, DynamoDB, Bedrock) for scalable inference and context management.
Optimize for low-latency, cost-efficient model execution across mobile, web, and live commerce channels.

Governance, Security & Compliance

Implement AI safety, prompt management, and content moderation layers within MCP.
Ensure secure handling of user data, conversation history, and AI outputs in compliance with privacy standards.

Mentorship & Leadership

Guide the team on AI/LLM engineering best practices, prompt engineering, and multi-agent system design.
Collaborate cross-functionally with product, engineering, and ML Ops teams to align AI initiatives with business goals.

Qualifications
AI / LLM Engineering Expertise

8+ years of experience in software engineering with a focus on AI, LLMs, and conversational systems.
Strong experience with LLM deployment, prompt chaining, and context management systems.
Expertise in vector databases (Pinecone, Weaviate, Milvus, Redis), embeddings, and RAG pipelines.

Model Context Protocol & AI System Design

Proven ability to design context-aware, memory-augmented AI systems.
Familiarity with agent orchestration frameworks (LangChain, LlamaIndex, or custom-built agents).

Backend & Cloud Collaboration

Proficiency in Node.js, TypeScript, Python, and GraphQL API integration for AI-driven applications.
Experience building event-driven, serverless architectures on AWS.

Bonus (Nice to Have)

Experience with real-time commerce agents, AI-driven personalization in retail, or fashion tech applications.
Background in agentic AI systems, tool use with LLMs, or live shopping automation.
Familiarity with MLOps, model versioning, and feedback loop systems.

Required profile