GrowthX AI is hiring an AI Engineer (Software Engineer, AI and Agent) to build the AI systems powering our content generation platform. You will design, build, and ship core agent workflows and model-driven features that help customers create content humans alone can’t produce, and AI alone shouldn’t. Your work will bridge breakthrough research to production, ensuring quality, safety, and continuous improvement at scale.

What You'll Do

Build and iterate on LLM features and components for our agentic workflow platform powering expert-guided content generation.
Design and maintain APIs and services for inference and workflow execution used by internal and external customers.
Improve model performance through eval systems, prompt optimization, retrieval-augmented generation (RAG), and fine-tuning.
Benchmark and optimize performance, cost, and latency across the inference stack.
Strengthen reliability, observability, testing, and deployment practices for AI systems.
Scale platform components to support rapid experimentation and learning from human feedback.
Identify and integrate relevant advances in AI tooling and research into production features.

What We're Looking For

6+ years building scalable backend systems or platforms in production.
Strong coding skills and comfort with service-oriented architectures.
Experience shipping ML/LLM-powered applications.
Strong understanding of foundation models, prompt engineering, and evals methods.
Ability to make clear tradeoffs between quality, speed, and cost in production systems.
Hands-on experience in fast-moving product environments and 0→1 systems.
Takes full ownership of projects and operates well with ambiguity.
Bachelor’s degree in CS/Software Engineering or equivalent experience.

Nice to Have

Experience building agent applications with tool calling, context engineering, MCP, and open connector integrations.
Familiarity with the trade-offs between major LLM architectures impacting quality, cost, and latency in production.
Experience improving LLM serving performance in production (e.g., continuous batching, quantization, GPU utilization).
Experience developing evaluation or quality-control systems for ML products.
Experience contributing to open-source model tooling or post-training workflows.
Familiarity with frameworks like LangGraph, AutoGen, LlamaIndex agents, etc.
Experience with Temporal is a plus.