Job
Description
As a highly skilled and experienced Senior Research Lead for Speech, Audio, and Conversational AI at Krutrim, your role involves spearheading research and development in cutting-edge technologies related to speech processing, text-to-speech (TTS), audio analysis, and real-time conversational AI. Collaborating with a team of talented engineers and researchers, you will design, implement, and optimize state-of-the-art systems to enhance the quality of speech and audio solutions for various applications. Key Responsibilities: - Bring advanced Audio Language Models and Speech Language Models by leveraging the state of the art in Audio/Speech and Large Language Models. - Research, architect, and deploy new generative AI methods like autoregressive models, causal models, and diffusion models. - Develop low-latency end-to-end models using multilingual speech/audio as input and output. - Evaluate and enhance model performance focusing on accuracy, naturalness, efficiency, and real-time capabilities across multiple languages through experiments. - Remain updated with the latest advancements in speech processing, audio analysis, and large language models to incorporate new techniques into foundation models. - Collaborate with cross-functional teams to integrate these models into Krutrim's AI stack and products. - Publish research findings in esteemed conferences and journals such as INTERSPEECH, ICASSP, ICLR, ICML, NeurIPS, and IEEE/ACM Transactions on Audio, Speech, and Language Processing. - Mentor junior researchers and engineers to foster a collaborative and innovative team environment. - Drive the adoption of best practices in model development, including testing, documentation, and ethical considerations in multilingual AI. Qualifications: - Ph.D. with 5+ years or MS with 8+ years experience in Computer Science, Electrical Engineering, or related field focusing on speech processing, audio analysis, and machine learning. - Proficiency in training or finetuning speech/audio models for representation, generation, and multilingual multitask models. - Expertise with Audio Language Models like AudioPALM, Moshi, and Seamless M4T. - Demonstrated track record in developing novel neural network architectures such as Transformers, Mixture of Experts, Diffusion Models, and State Space Machines. - Extensive experience in optimizing models for low-latency, real-time applications. - Strong background in multilingual speech recognition and synthesis with an understanding of language-specific challenges. - Proficiency in deep learning frameworks like TensorFlow, PyTorch, and deploying large-scale speech and audio models. - Expertise in high-performance computing with proficiency in Python, C/C++, CUDA, and kernel-level programming for AI applications. - Experience with audio signal processing techniques and their application in end-to-end neural models. - Strong publication record in top AI conferences and journals, particularly focusing on speech, audio, and language models. - Excellent communication skills to convey complex technical concepts to technical and non-technical audiences.,
