ML Platform and Inference Engineer – Content Developer

This is a fully remote position, open to applicants in Argentina, +5 more countries.

📋 Description

• Create module content for the Master's program in AI Systems Engineering

• Design laboratory exercises

• Develop a reference implementation

• Construct an evaluation harness

• Prepare a guide for instructors

• Personally produce the course artifact to meet production standards

• Transfer the developed materials to the program for use by other instructors

⛳️ Requirements

• Over 5 years of experience in delivering production software, with at least 2 years focused on production AI/ML

• Capable of personally producing the course artifact to meet production standards

• Publicly available proof of technical writing (documentation, technical blog, open-source projects)

• Strong discipline in reproducibility (including pinned dependencies, containers, and seeded runs)

• Proficient in written English

• Open to handing over developed materials to the program (as the course will be taught by other instructors)

• Proven experience in fine-tuning classical ML and small foundation models

• Background in shipping containerized inference services into production

• Experience with multi-tenant serving in production environments (including routing, queueing, and isolation)

• Successful track record in quantization and caching, demonstrating cost reduction in serving

• Familiarity with Docker, Modal, Hugging Face Hub, scikit-learn, PyTorch, vLLM, Prometheus, Grafana, and Locust or k6

🏝️ Benefits

• Flexible remote work arrangement (home office)

• Opportunity to join a vibrant and expanding organization with a global presence