Machine Learning Engineer (Benchmarking and Evaluation)

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 its clients by accelerating frontier research through high-quality data, sophisticated training pipelines, and top-tier AI researchers specializing in coding, reasoning, STEM, multilinguality, multimodality, and agents. Additionally, Turing helps enterprises transform AI from proof of concept into proprietary intelligence by delivering systems that perform reliably, provide measurable impact, and generate lasting results on the P&L. The company's innovative approach and commitment to excellence have established it as a leader in the AI research and deployment space, fostering a collaborative environment where cutting-edge AI solutions are developed and implemented at scale.

About The Role

We are seeking experienced Machine Learning Engineers (MLE Bench) to join our team and contribute to benchmark-driven evaluation projects focused on real-world machine learning systems. This role involves working directly with production-grade ML codebases, developing and refining model training and evaluation pipelines, and supporting deployment workflows. The primary goal is to assess and enhance the capabilities of advanced AI systems through rigorous benchmarking and evaluation. The ideal candidate will possess a strong ability to bridge research and engineering, working deeply with models, data, and infrastructure in realistic ML environments. You will collaborate closely with research teams and engineers to design challenging evaluation tasks, debug complex systems, and ensure the robustness and performance of AI models in practical settings. This position offers a unique opportunity to work on impactful projects that push the boundaries of AI technology and contribute to the development of reliable, scalable AI systems.

Qualifications

The ideal candidate will have at least 3+ years of experience as a Machine Learning Engineer or Software Engineer with a focus on ML. Proficiency in Python is essential, particularly for building and maintaining data workflows, model training, and evaluation pipelines. Hands-on experience with model training, inference, and evaluation is required, along with a solid understanding of machine learning fundamentals such as supervised and unsupervised learning, evaluation metrics, and optimization techniques. Candidates should have experience working with popular ML frameworks like PyTorch, TensorFlow, JAX, or similar tools. The ability to understand, navigate, and modify complex, real-world ML codebases is crucial. Strong problem-solving and debugging skills are necessary, as well as excellent communication skills in spoken and written English. Candidates should demonstrate a commitment to writing clean, maintainable, and reproducible code, and possess the ability to collaborate effectively within cross-functional teams.

Responsibilities

As a Machine Learning Engineer in this role, your responsibilities will include working with real-world ML codebases to support evaluation tasks aligned with benchmarking standards. You will build, run, and modify model training, evaluation, and inference pipelines to ensure accuracy and performance. Preparing datasets, features, and metrics for benchmarking and validation is a key part of your work. You will debug, refactor, and optimize production-like ML systems to improve their correctness and efficiency. Evaluating model behavior, identifying failure modes, and analyzing edge cases relevant to benchmark tasks will help inform system improvements. Writing clean, well-documented Python code for ML workflows is essential, along with participating in code reviews to uphold high engineering standards. Collaboration with researchers and engineers to design challenging evaluation scenarios will be a core aspect of your role, ensuring that AI systems are tested rigorously in realistic environments.

Benefits

Joining Turing as a freelance Machine Learning Engineer offers the flexibility of working in a fully remote environment, allowing you to balance your professional and personal commitments. 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 provides exposure to innovative technologies and the chance to contribute to impactful research and development initiatives. Additionally, Turing offers a competitive engagement structure, allowing you to work at least 4 hours per day and a minimum of 20 hours per week, with a minimum overlap of 4 hours with PST. The initial contract duration is three months, with potential for extension based on performance and project needs. Freelancers also benefit from the opportunity to expand their professional network and earn additional income through referrals.

Equal Opportunity

Turing is committed to fostering an inclusive and diverse work environment. We are an equal opportunity employer and do not discriminate based on race, religion, gender, sexual orientation, age, disability, or any other protected characteristic. We believe in providing equal access to employment opportunities and creating a workplace where all employees can thrive and contribute to our mission of advancing AI research and deployment. We welcome applicants from all backgrounds and are dedicated to supporting a culture of respect, collaboration, and innovation.