AI Systems Engineer (LLM / Agents / RAG)

AI Systems Engineer (LLM / Agents / RAG)

Remote | Full-time | Flexible Schedule

Our client is looking for a strong AI Systems Engineer to help design and build production-grade AI infrastructure, agent-based systems, and workflow automation.

You’ll work directly with the Head of AI on building the company’s internal AI ecosystem: multi-agent systems, RAG pipelines, AI-powered analytics, automation workflows, integrations, and operational AI tooling.

This role is ideal for someone who enjoys building real AI systems end-to-end — not just experimenting with prompts, but designing scalable architectures and shipping production-ready solutions.

Responsibilities

• Design and develop production AI/LLM systems
• Build agent-based workflows and multi-agent orchestration systems with memory, routing, and tool usage
• Develop end-to-end RAG pipelines and knowledge base systems:
  • ingestion
  • chunking
  • embeddings
  • retrieval
  • vector databases
  • citation tracing
  • hallucination mitigation
• Build AI-powered workflow automation for marketing, analytics, operations, and reporting
• Integrate LLM systems with CRMs, APIs, external platforms, and internal tools
• Develop integrations using REST APIs, webhooks, and third-party services
• Participate in building unified analytics and attribution systems across multiple channels and platforms
• Support creative/content AI pipelines (image/video generation workflows)
• Improve reliability, observability, latency, and cost-efficiency of AI systems
• Deploy and maintain AI systems in production environments
• Work closely with the Head of AI on architecture and AI ecosystem development

Requirements

• 2+ years of hands-on experience building production AI/LLM systems (not educational or pet projects)
• Strong Python skills
• Experience building production backend systems and integrations
• Practical experience with:
  • agent orchestration frameworks (LangGraph-class frameworks)
  • tool/function calling
  • structured outputs
  • guardrails
  • multi-agent systems
• Strong understanding of RAG systems and retrieval pipelines
• Experience with vector databases:
  • Pinecone
  • Qdrant
  • pgvector
• Experience with PostgreSQL and data-layer architecture
• Understanding of:
  • embeddings
  • chunking strategies
  • retrieval quality
  • citation tracing
  • hallucination mitigation
• Experience with workflow automation tools:
  • n8n
  • Make
  • Zapier
  • or similar
• Basic LLMOps understanding:
  • evals
  • observability (Langfuse-class tooling)
  • latency optimization
  • cost optimization
  • fallback model chains
• Experience working with OpenAI and/or Anthropic Claude APIs
• Understanding of MCP (Model Context Protocol)
• Experience with REST APIs, webhooks, and external integrations
• English level: B1+

Nice to Have

• Experience with AI automation for marketing, analytics, or operations
• Experience with e-commerce ecosystems:
  • Shopify
  • Amazon
  • TikTok Shop
  • marketplace analytics
• Experience with attribution or marketing analytics systems
• Experience with image/video generation workflows or ComfyUI
• Understanding of privacy/compliance concepts (CCPA-class requirements)
• Portfolio or GitHub with production AI projects

What Matters in This Role

• Strong ownership mindset
• Ability to translate business problems into working AI architectures
• Production-oriented engineering mindset
• Ability to work independently in async environments
• Focus on measurable and reliable AI systems rather than experimental demos

We Offer

• Fully remote work from anywhere
• Flexible schedule
• Direct collaboration with the Head of AI
• Modern AI stack and real production AI challenges
• High ownership and technical freedom
• Paid vacation and sick days