LLM Model training for Coding

2 weeks ago


bangalore, India DeepLLMData Full time

Company DescriptionDeepLLMData specializes in driving advancements in AI by providing expertly curated human data to power frontier models. With expertise in Coding SFT (Supervised Fine-Tuning) and Reinforcement Learning with Human Feedback (RLHF), the company collaborates with domain-specific experts across STEM, Mathematics, PhD fields, and more. DeepLLMData also offers image and video annotation services, along with data provisioning for diverse machine learning applications. Our team’s mission is to support AI excellence globally.Role DescriptionThis is a contract-based, remote role for an expert in training Large Language Models (LLMs) with a specialization in C/C++ programming and a minimum of 3 years of professional experience. The primary responsibilities include curating and annotating high-quality coding data, assessing and enhancing LLM performance for coding tasks, collaborating with a team of AI researchers, and contributing to the training process of models through techniques like supervised fine-tuning and RLHF. The ideal candidate will also assist in evaluating outputs and providing insights to improve the DSQualificationsAdvanced proficiency in C and C++ programming with at least 3 years of professional experience.Strong understanding of machine learning concepts, supervised fine-tuning, and reinforcement learning with human feedback (RLHF).Experience in data annotation, curating, and preprocessing for AI model training is a Plus.Background in software engineering or AI development, with a focus on large-scale language models or coding-related tasks.Excellent problem-solving skills, attention to detail, and ability to work independently in a remote setting.Bachelor’s or advanced degree in Computer Science, Software Engineering, or related technical field is required; Master’s or PhD is a plus.



  • bangalore, India DeepLLMData Full time

    Company Description DeepLLMData specializes in advancing frontier models by leveraging expert human data. The organization focuses on coding techniques like Supervised Fine-Tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF). In addition, DeepLLMData collaborates with specialists in STEM fields, applied mathematics, and domain-specific areas....


  • bangalore, India DeepLLMData Full time

    Company Description DeepLLMData specializes in advancing frontier models by leveraging expert human data. The organization focuses on coding techniques like Supervised Fine-Tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF). In addition, DeepLLMData collaborates with specialists in STEM fields, applied mathematics, and domain-specific areas....


  • bangalore, India DeepLLMData Full time

    Company DescriptionDeepLLMData specializes in advancing frontier models by leveraging expert human data. The organization focuses on coding techniques like Supervised Fine-Tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF). In addition, DeepLLMData collaborates with specialists in STEM fields, applied mathematics, and domain-specific areas....


  • bangalore, India DeepLLMData Full time

    Company Description DeepLLMData specializes in providing expert human-generated data to power advanced frontier models. Our services include coding-specific supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF). We are committed to fostering innovation in various domains through our teams of experts in STEM, Mathematics, and...


  • bangalore, India DeepLLMData Full time

    Company Description DeepLLMData specializes in providing expert human-generated data to power advanced frontier models. Our services include coding-specific supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF). We are committed to fostering innovation in various domains through our teams of experts in STEM, Mathematics, and...


  • bangalore, India DeepLLMData Full time

    Company Description DeepLLMData specializes in providing expert human-generated data to power advanced frontier models. Our services include coding-specific supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF). We are committed to fostering innovation in various domains through our teams of experts in STEM, Mathematics, and...


  • bangalore, India DeepLLMData Full time

    Company Description DeepLLMData specializes in empowering advanced AI models with expertly curated human data. Our services include training data for Coding SFT (Supervised Fine-Tuning), RLHF (Reinforcement Learning with Human Feedback), and various STEM-related domains. With a focus on Python programming, we draw on skilled professionals, including...


  • bangalore, India DeepLLMData Full time

    Company DescriptionDeepLLMData specializes in empowering advanced AI models with expertly curated human data. Our services include training data for Coding SFT (Supervised Fine-Tuning), RLHF (Reinforcement Learning with Human Feedback), and various STEM-related domains. With a focus on Python programming, we draw on skilled professionals, including PhD-level...


  • bangalore, India DeepLLMData Full time

    Company Description DeepLLMData specializes in providing high-quality human data to power advanced machine learning models, including Coding SFT and RLHF. The company brings together experts in STEM fields, Mathematics, and domain-specific areas to develop and enhance AI models. DeepLLMData also offers image and video annotation services as well as data...


  • bangalore, India DeepLLMData Full time

    Company Description DeepLLMData specializes in providing high-quality human data to power advanced machine learning models, including Coding SFT and RLHF. The company brings together experts in STEM fields, Mathematics, and domain-specific areas to develop and enhance AI models. DeepLLMData also offers image and video annotation services as well as data...