Machine Learning Engineer (MLE Bench)

About The Company

Based in San Francisco, California, Turing is the world’s leading research accelerator for frontier AI labs and a trusted partner for global enterprises deploying advanced AI systems. Turing supports customers in two primary ways: first, by accelerating frontier research with high-quality data, advanced training pipelines, and top-tier AI researchers specializing in coding, reasoning, STEM, multilinguality, multimodality, and agents; and second, by applying that expertise to help enterprises transform AI from proof of concept into proprietary intelligence. Our systems are designed to perform reliably, deliver measurable impact, and drive lasting results on the profit and loss statements of our clients. Turing’s innovative approach and commitment to excellence make us a pioneer in the AI industry, fostering groundbreaking research and enabling organizations worldwide to harness the full potential of artificial intelligence.

About The Role

We are seeking experienced Machine Learning Engineers (MLE Bench) to join our team and contribute to benchmark-driven evaluation projects centered on real-world machine learning systems. This role involves hands-on work with production-grade ML codebases, model training and evaluation pipelines, and deployment-oriented workflows. The primary objective is to assess and enhance the capabilities of advanced AI systems through rigorous benchmarking and validation. The ideal candidate will possess a strong ability to bridge research and engineering, working deeply with models, data, and infrastructure within realistic ML environments. This position offers an exciting opportunity to be at the forefront of AI evaluation, ensuring that state-of-the-art models meet the highest standards of performance, robustness, and reliability.

Qualifications

The successful candidate should have a minimum of 3+ years of experience as a Machine Learning Engineer or Software Engineer with a focus on ML. Proficiency in Python is essential, particularly for developing and managing data workflows and ML pipelines. Hands-on experience with model training, evaluation, and inference pipelines is required, along with a solid understanding of fundamental machine learning concepts such as supervised and unsupervised learning, evaluation metrics, and optimization techniques. Experience working with popular ML frameworks like PyTorch, TensorFlow, or JAX is highly desirable. Candidates must be capable of understanding, navigating, and modifying complex, real-world ML codebases. Strong problem-solving and debugging skills are crucial, as well as excellent communication skills in spoken and written English to facilitate effective collaboration across teams.

Responsibilities

The role involves working with real-world ML codebases to support evaluation tasks aligned with MLE Bench standards. Responsibilities include building, running, and modifying model training, evaluation, and inference pipelines to ensure robustness and performance. You will prepare datasets, features, and metrics for benchmarking and validation purposes, ensuring reproducibility and accuracy. Debugging, refactoring, and enhancing production-like ML systems for correctness and efficiency will be a key part of your daily activities. Additionally, you will evaluate model behavior, identify failure modes, and analyze edge cases relevant to benchmark tasks. Writing clean, well-documented, and reproducible Python code is essential to maintain high standards of engineering quality. You will also participate in code reviews and collaborate with researchers and engineers to design challenging, real-world ML engineering tasks for comprehensive AI system evaluation.

Benefits

As a freelancer with Turing, you will enjoy the flexibility of working in a fully remote environment, allowing you to balance your professional and personal life effectively. You will have the opportunity to work on cutting-edge AI projects with leading companies specializing in large language models and advanced AI systems. This role offers a competitive engagement structure with a commitment of at least 4 hours per day, totaling a minimum of 20 hours per week, with an overlap of 4 hours with PST. The initial contract duration is three months, with potential for extension based on performance and project needs. Turing also provides a platform for talented professionals to grow their expertise in the rapidly expanding AI landscape, along with opportunities for networking and professional development.

Equal Opportunity

Turing is committed to fostering an inclusive and diverse work environment. We provide equal employment opportunities to all qualified applicants regardless of race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, disability, or any other protected characteristic. We believe that diversity drives innovation and excellence, and we strive to create a workplace where every individual feels valued, respected, and empowered to contribute their best.