Staff AI Engineer

This is a fully remote position, open to applicants in Illinois.

📋 Description

• Architect and develop enterprise-level multi-agent systems utilizing LLMs and autonomous agent frameworks.

• Design and execute RAG pipelines using BigQuery and Vertex AI Engine to ensure knowledge grounding and precise responses.

• Optimize agents for orchestration, knowledge grounding, multi-step reasoning, and decision-making processes.

• Design and implement distributed training workflows, online inference systems, and architectures for low-latency serving.

• Build scalable, secure, compliant, and production-ready AI fabric along with agent workflows.

• Develop reusable agent orchestration layers, observability hooks, and governance frameworks.

• Collaborate with cross-functional stakeholders to convert business requirements into technical specifications.

• Take ownership of the entire AI development lifecycle, from data collection and implementation to deployment and monitoring.

• Apply observability and automation strategies to guarantee the reliability and performance of AI systems at scale.

⛳️ Requirements

• Bachelor's degree in Computer Science, a related technology field, or equivalent experience.

• Over 2 years of experience in Agentic AI engineering.

• More than 4 years of experience in AI/ML engineering.

• At least 8 years of experience in software engineering or platform engineering.

• Documented success in building and deploying production-grade AI/ML systems at scale.

• Strong understanding of contemporary AI model architectures, including transformers and diffusion models, as well as system design.

• Practical knowledge of Vertex AI, encompassing model training, pipelines, orchestration, deployment, and monitoring, in addition to Google’s Agentic AI stack.

• Experience with one or more agent orchestration frameworks: Google ADK/Agentspace, LangChain, LangGraph, LlamaIndex, CrewAI, or AutoGen.

• Proficiency in Python, LLM integration workflows, MCP for tool integration, and A2A orchestration.

• Expertise in distributed training, online inference, and architectures for low-latency serving.

• Familiarity with Kubernetes, Cloud Run, and Dataflow/PubSub.

• Preferred: Knowledge of AI governance frameworks and responsible AI practices.

• Preferred: Contributions to open-source AI projects or leading publications at AI/ML conferences.

• Preferred: Experience with multi-modal models and advanced optimization strategies and frameworks.

• Preferred: Automation of production-grade MLOps infrastructure, including architecture, governance, scaling, optimization, and observability.

🏝️ Benefits

• Paid time off

• Health insurance

• Dental insurance

• Vision insurance

• 401(k) savings plan with match

• Generous benefits package