Artificial Intelligence Engineer

Job OverviewSeeking a highly skilled AI Engineer with strong hands-on experience in designing, building, and deploying LLM-powered systems in production environments. This role focuses on developing scalable AI applications using modern agent frameworks and API-driven architectures. The ideal candidate brings deep expertise in Python, LLM orchestration, and backend service development, with a strong understanding of production-grade AI workflows. Key ResponsibilitiesDesign, develop, and deploy LLM-driven applications and intelligent agent-based systems.Build and integrate LLM orchestration pipelines, including prompting strategies, tool usage, memory, and workflow coordination.Develop scalable, production-ready backend services and APIs using FastAPI.Implement agent workflows leveraging LangChain and LangGraph, including graph-based orchestration and state management.Design and evaluate LLM pipelines, including model selection, evaluation, and performance optimization.Collaborate with cross-functional teams to integrate AI capabilities into existing platforms and services.Ensure system reliability, performance, and maintainability in production environments.Apply best practices for asynchronous execution, API security, and system scalability. Required Qualifications8–10 years of professional experience in AI, ML, or LLM-based system development.Strong proficiency in Python, with experience building production-grade backend and data/ML workflows.Hands-on experience with LLM integration, including prompting, orchestration, and pipeline design.Proven experience with LangChain and LangGraph, including agent frameworks, tools, memory, and graph-based workflows.Solid experience developing robust APIs and backend services using FastAPI.Strong understanding of modern software engineering best practices and API-driven architectures. Technical SkillsProgramming & Frameworks: Python, FastAPILLM & Agent Frameworks: LangChain, LangGraphAI Capabilities: Prompt engineering, agent orchestration, model evaluation, pipeline designBackend Systems: Async execution, API gateways, scalable service design Preferred SkillsExperience deploying AI systems in cloud or containerized environments.Familiarity with monitoring, logging, and evaluation of LLM performance in production.Strong problem-solving skills and the ability to work in fast-paced, evolving AI environments. Pay: $65.00 - $75.00 per hour Expected hours: 40.0 per week Experience: AI/LLM/ML: 7 years (Required) Fast API: 3 years (Required) Python: 7 years (Required) LangGraph and LangChain: 4 years (Required) Ability to Commute: Newark, CA 94560 (Required) Work Location: Hybrid remote in Newark, CA 94560