AI Automation Engineer/ Sr. AI Automation Engineer

Accountabilities

• Partner with business teams to transform AI proofs of concept into secure, scalable, production-ready applications, including dashboards, reporting tools, chatbots, support agents, and internal business applications.
• Design, develop, and deploy reusable AI agents, automation workflows, and intelligent integrations powered by large language models (LLMs).
• Integrate AI capabilities with enterprise platforms and business systems, including CRM, collaboration, ERP, and database solutions.
• Build and maintain cloud-native applications on a governed Google Cloud Platform (GCP) environment, ensuring reliability, scalability, and operational excellence.
• Implement authentication, access controls, secrets management, CI/CD pipelines, monitoring, logging, and version control to harden applications for production.
• Create automated processes to maintain software dependencies, improve application security, and reduce operational overhead.
• Develop evaluation frameworks, regression testing, and observability solutions to monitor AI model performance, retrieval quality, application health, and overall system reliability.
• Collaborate with cross-functional stakeholders to translate evolving business requirements into maintainable, high-quality software solutions while continuously improving AI engineering practices.

Requirements

• 5+ years of experience designing, building, and deploying production software, automation solutions, or data-driven applications.
• Strong programming skills in Python and solid experience working with SQL and enterprise data environments.
• Hands-on experience deploying and operating cloud-native applications, preferably on Google Cloud Platform (GCP).
• Strong understanding of production engineering fundamentals, including authentication, identity management, secrets management, CI/CD, logging, monitoring, and infrastructure operations.
• Experience integrating enterprise applications through APIs and SaaS platforms.
• Ability to work directly with business stakeholders and translate functional requirements into scalable technical solutions.
• Experience building LLM-powered applications, AI agents, retrieval-augmented generation (RAG) pipelines, tool/function calling, or agentic workflows is highly desirable.
• Familiarity with AI evaluation and observability platforms such as LangSmith, Langfuse, Braintrust, or similar tools.
• Experience with vector databases and retrieval technologies, including Vertex AI Vector Search, Pinecone, pgvector, or equivalent solutions, is a plus.
• Strong analytical thinking, problem-solving, communication, collaboration, and continuous learning mindset.

Benefits

• Competitive base salary ranging from $80,000 to $160,000 USD, based on experience, skills, and qualifications.
• Fully remote work opportunity within the United States.
• Comprehensive medical, dental, and vision insurance.
• Paid vacation and company holidays.
• Dedicated Health & Wellness Days.
• Birthday bonus day off.
• Eligibility for additional performance-based compensation, including bonus or commission, depending on the role.
• Flexible, collaborative work environment that supports professional growth and innovation.
• Inclusive culture that values diverse backgrounds, continuous learning, and career development.