About the company
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior Artificial Intelligence/Machine Learning Engineer based in United States.
Responsibilities
- Design and develop production-grade agentic AI systems that can reliably support real enterprise users and business workflows.
- Build autonomous agents using Glean as the agent platform and OpenAI/GPT Enterprise as the reasoning layer, deployed within AWS or GCP environments.
- Own AI agents throughout their full lifecycle, including architecture, implementation, production deployment, monitoring, evaluation, troubleshooting, and iteration.
- Design robust agent workflows incorporating triggers, retrieval, multi-step reasoning, tool and function calling, actions, permissions, and memory.
- Implement retrieval-augmented generation and enterprise search capabilities while ensuring high-quality retrieval and appropriate runtime permission enforcement.
- Establish evaluation frameworks and measurable quality standards to assess agent performance systematically rather than relying solely on manual inspection.
- Optimize AI systems for reliability, security, maintainability, cost efficiency, and latency at enterprise scale.
- Apply strong observability and production engineering practices to identify issues, improve system performance, and support continuous iteration.
Requirements
- Bring 3+ years of hands-on experience building and operating LLM-powered systems in production environments used by real customers or users.
- Demonstrate practical experience designing agentic AI workflows, including tool and function calling, retrieval-augmented generation (RAG), multi-step orchestration, and memory.
- Have deep hands-on experience with the OpenAI API and GPT Enterprise, including model selection, prompt engineering, structured outputs, function calling, cost and latency optimization, and enterprise data-handling controls.
- Demonstrate strong prompt-engineering discipline and an evaluation-first mindset, with experience using measurable evaluations to assess and improve agent quality.
- Have direct, hands-on production experience with Glean, including Agent Builder, Apps, Actions, Model Hub, connectors, and permission-aware retrieval; this is a mandatory requirement for the role.
- Possess working knowledge of enterprise search and RAG architectures on Glean, including indexing, connectors, retrieval quality, and runtime permission enforcement.
- Understand how to approach AI agents as production software, with strong awareness of reliability, security, observability, scalability, and maintainability.
- Demonstrate strong analytical and problem-solving abilities, combined with the ability to work independently on technically complex AI engineering challenges.
- Communicate effectively with technical and business stakeholders and collaborate within a global, multidisciplinary engineering environment.
Conditions
- Work alongside highly skilled technology professionals in a collaborative, friendly, and open-door environment.
- Contribute to large-scale projects with global impact while expanding your expertise in advanced AI and machine learning technologies.
- Access tailored learning opportunities, including internal meetups, conferences, workshops, Udemy courses, language training, and company-paid certifications.
- Explore internal mobility opportunities across diverse domains and projects to build hands-on experience with emerging technologies.
- Benefit from healthcare coverage, Basic Life Insurance, and short- and long-term disability insurance in accordance with the applicable benefits plans.
- Work remotely from Canada while contributing to enterprise-scale AI initiatives and innovative technology projects.