Description

Requirements

6 years or more of software or AI engineering experience building production-grade LLM applications and services.

Proficiency in Python for developing scalable backend services, APIs, and AI-enabled applications.

Experience with LangChain, LangGraph, LlamaIndex, OpenAI APIs, Anthropic APIs, MCP, or comparable AI frameworks.

Experience in RAG, prompt engineering, tool calling, agent workflows, context management, and structured generation.

Experience with cloud-native AI architecture, deployment, evaluation, observability, and monitoring on AWS, Azure, or Google Cloud Platform.

Excellent verbal and written communication skills.

Responsibilities

Build and deploy scalable LLM applications, AI assistants, agent workflows, and automation solutions.

Develop orchestration layers supporting prompting, retrieval, context handling, and external tool integration.

Prototype and refine AI solutions based on enterprise workflows, stakeholder feedback, and operational challenges.

Implement testing, evaluation, guardrails, monitoring, and performance improvements for production AI systems.

Create reusable AI engineering patterns, SDK examples, technical guides, and enablement materials.

Partner with product, engineering, data science, UX, security, and subject-matter teams on AI delivery

Key Skills

Education

Bachelor's degree