Binit Bhattarai

My name is Binit Bhattarai, and I am a computer scientist and engineer passionate about building intelligent systems that solve real-world problems, particularly in healthcare and speech technologies. I completed my Bachelor of Technology in Computer Science and Engineering at Vellore Institute of Technology, India, where I graduated with first-class honors and a CGPA of 9.09 out of 10. My education was fully funded through the COMPEX Scholarship from the Embassy of India to Nepal, an opportunity that not only eased my financial journey but also motivated me to push myself to excel academically and professionally.

Currently, I work as a Software Engineer at Infinite Computer Solutions in Kathmandu, where I contribute to DxCG Intelligence, a predictive risk management and healthcare analytics platform used by Cotiviti. My role allows me to combine software engineering with healthcare innovation—two areas I deeply care about. I design modular features such as reporting dashboards, license authorization, and client usage tracking using Java and Angular, all within agile development practices. I also introduced Dockerized environments and CI/CD pipelines to streamline our workflows, which significantly improved reliability and accelerated release cycles. One of my proudest achievements here has been creating a performance runner tool that automated test execution and generated comparative reports, reducing manual testing efforts by nearly 80%.

Before joining Infinite, I had the privilege of conducting research at A*STAR in Singapore as part of the SIPGA program. There, I worked on projects in speech and audio processing, including automatic speech recognition, singing voice synthesis, speech enhancement, and dementia detection through audio classification. I curated large-scale datasets, including an Indonesian speech corpus and a specialized singing corpus that was later published at APSIPA. My technical focus was on fine-tuning models such as Whisper, Wav2Vec2, and WavLM, as well as experimenting with VITS and diffusion architectures for high-quality singing voice synthesis. This experience not only sharpened my machine learning skills but also reinforced my belief in the transformative role AI can play in healthcare and assistive technologies.

Earlier, I worked as a Research Intern at Samsung Research Institute in Bangalore, where I contributed to the IoT Edge Project through the PRISM program. My work involved kernel-level programming on TizenRT, where I developed and integrated a Network File System client library for low-memory devices. This helped address storage limitations in resource-constrained environments and taught me how to innovate under hardware and efficiency constraints.

Alongside my professional journey, I have co-authored conference papers, including one on self-attention Siamese networks for unsupervised few-shot learning (ISPR 2024) and another on developing a high-quality Vietnamese singing voice corpus (APSIPA 2024). These experiences in research and publication have given me a strong foundation for future academic and industrial contributions.

Beyond my technical life, I value curiosity, collaboration, and continuous learning. I am fluent in multiple languages, including Nepali, English, Hindi, and French, which has helped me connect across cultures and teams. Ultimately, my goal is to use my skills in AI, software engineering, and research to build technologies that are not only intelligent but also impactful for people’s lives.