LLM Platform Engineer - Production AI Pipelines

Quadcode; Georgia; Hybrid; USD 120,000 - 180,000; Full time

Job summary

Quadcode seeks an AI Engineer to join its AI Platform team, focusing on designing, building, and maintaining production generative AI pipelines and LLM-powered features that often handle financial and trading data.

You will work on agentic systems with MCP integrations, implement backend services in Python atop OpenAI/Anthropic/xAI APIs or on-premise deployments, and refine prompt engineering and evaluation pipelines for reliable production systems.

Qualifications

• Production LLM features shipped with OpenAI and/or Anthropic or on-premise models.
• Hands-on multi-agent systems development and MCP server experience.
• Proficient Python with API design, databases, Docker, and version control.
• Experience with structured outputs, prompt evaluation, and cost-aware design.
• English fluency in written and spoken communication.

Responsibilities

• Design, build, and maintain LLM-powered features and pipelines for generative AI products, including systems that process financial and trading content.
• Develop and improve agentic systems and multi-agent workflows, including MCP server integrations.
• Implement production-grade backend services in Python on top of LLM provider APIs and/or on-premise deployments.
• Build and iterate on prompt engineering and evaluation pipelines with structured outputs and validation.
• Convert prototypes into reliable, maintainable production services.
• Monitor LLM cost, latency, and reliability trade-offs across end-to-end pipelines.
• Collaborate with a senior AI Platform team on architecture, code review, and technical direction.

Skills

Production LLM experience

Multi-agent workflow experience

Python proficiency

LLM engineering skills

English fluency

Tools

REST APIs

SQL

Docker

Git

Concurrency

Job description

Quadcode seeks an AI Engineer to join its AI Platform team, focusing on designing, building, and maintaining production generative AI pipelines and LLM-powered features that often handle financial and trading data.

You will work on agentic systems with MCP integrations, implement backend services in Python atop OpenAI/Anthropic/xAI APIs or on-premise deployments, and refine prompt engineering and evaluation pipelines for reliable production systems.