Aditya Sneh

One thing I’m oddly proud of is convincing people to let their phones become research instruments. I built a mobile sensing system that collected 250+ GB of real-world behavioral and sensor data from 70+ participants, which meant dealing with everything from noisy signals to phones deciding they didn’t feel like cooperating that day. Turning that messy, real-world data into ML models that could actually learn something useful was both frustrating and incredibly fun.

Along the way, this work also led to several research publications, including a paper at BMVC 2025 and ongoing research exploring behavioral modeling, few-shot learning, and multimodal stress detection.

I enjoy problems where data isn’t clean, systems must survive outside the lab, and models have to deal with the real world instead of perfectly curated datasets.

Project Junior Research Fellow at Systems and Informatics Research Laboratory (2024-08 – Present)

Built and deployed machine learning systems for mobile sensing and adaptive intervention research

• Built and deployed LogMe, a 24×7 Android (Kotlin) sensing platform that collected 250+ GB of real-world mobile sensor and usage data from 70+ participants over 14 days, backed by Apache/Python REST APIs and MySQL for reliable ingestion.
• Engineered notification-triggered labeling workflows capturing user activity, social context, intervention feasibility, and mood for supervised learning and adaptive real-time modeling.
• Developed and fine-tuned DySTAN (Dynamic Cross-Stitch, Cross-Task Attention, BiLSTM), achieving 0.852/0.876 macro-F1 with +21.8% improvement over a CNN-BiLSTM-GRU baseline.
• Built end-to-end ML pipelines (segmentation, downsampling) for production ML systems and implemented a contextual multi-armed bandit (Thompson Sampling) for real-time optimization, exceeding the 0.5 intervention reward baseline.
• Collaborated with an AIIMS psychiatrist to integrate domain expertise into adaptive intervention policies; developed a Streamlit dashboard for real-time monitoring, model evaluation, and automated data validation.

Gen AI Subject Matter Expert (SME) at Grades Buddy (2024-05 – 2024-07)

Delivered production-grade GenAI solutions for support automation and healthcare applications

• Delivered 40+ production-grade GenAI solutions, building and deploying LLM-based and generative models (GANs, diffusion) for support automation, document intelligence, healthcare support, and data-driven workflows.
• Built and fine-tuned transformer-based architectures (LLaMA 2/3, Mistral 7B, BERT) via Hugging Face, implementing sentiment analysis, contextual generation, and RAG pipelines achieving 85% task accuracy.
• Applied LoRA-based PEFT for efficient domain adaptation and improved response reliability in LLM systems, including medical chatbot deployments.
• Developed a real-time speech-based sentiment classification system using Whisper for transcription and PyTorch classifiers, supporting scalable customer audio analysis.

BS-MS in Data Science & Engineering – Indian Institute of Science Education and Research (IISER) (2019 – 2024)