Autonomous AI/ML Research Scientist – Timothy K Johnsen

Resume

CV

TTimothy Kevin Johnsen
tjohnsen@uci.edu | Irvine, CA, USA | https://timkjohnsen.com/

SUMMARY

I am a PhD Candidate in Computational Science, set to graduate in June 2026, and looking for new career opportunities. My research focuses on Machine Learning (ML), Reinforcement Learning (RL), and agentic AI (vehicle and science autonomy); with a specialty in adaptive dynamic deep neural networks. I have a proven track record in developing full autonomy stacks and predictive model-based pipelines, as supported by eight peer-reviewed publications as lead author across UCI, NASA, LBNL, and industry. I am an expert in parallel and High Performance Computing (HPC) for training multimodal machine learning models and large-scale data processing, while simultaneously optimizing compute-heavy pipelines for improved inference efficiency, especially for deployment to resource constrained devices. I uniquely have an interdisciplinary background in STEM, emphasizing: rigorous experimental design, iterative model improvement, deeper understanding of physics-based and statistical methods, and effective collaborative communications with domain experts. Please see my personal website for a research summary that more lucidly demonstrates end-to-end methods that I develop.

SKILLS

  • Machine Learning: reinforcement (TD3, DQN), deep (scratch, pre, post), imitation, multimodal large language models (Gemma3), visual language action 
  • Neural Networks: adaptive, dynamic, gated, slimmable, split, CNN, MLP, GCN, U-Net, RNN, LSTM, transformer, auto-encoder, monte carlo dropout, model reduction, knowledge distillation, quantization, direct design, pruning, hyperparameter optimization
  • Methods: agentic AI, closed loop systems, Hardware-In-the-Loop (HIL), sim-to-real, sensor fusion, denoising and gap-filling, shortest path, ARIMA, finite differencing schemes, uncertainty quantification, spectra analysis, sensitivity analysis, Kalman filter
  • Tools: Python, C++, Java, PyTorch, Linux/Bash, SQL, Tensorflow, HPC, SLURM, AWS, Databricks, NVIDIA Jetson, Microsoft AirSim, Unreal Engine, DJI, APIs

RESEARCH & PROFESSIONAL EXPERIENCE

PhD Researcher | Intelligent and Autonomous Systems Lab, UC Irvine | 2021 – Present

  • Adaptive Models: Experiment with RL-based policies (TD3, DQN) that dynamically scale model complexity and sensor modalities in response to context at inference, by optimizing the trade-offs between test-time compute, power needs, and task accuracy.
  • Modular Pipelines: Iteratively train embedded slimmable and multi-branch split gated networks via RL and knowledge distillation to implement computationally complex models on real-world, resource-constrained hardware (NVIDIA Jetson).
  • Agentic AI: Design hierarchical VLA frameworks leveraging generative methods (diffusion policy) for high-level waypoint generation and planning, and RL for low-level robot embodiment control and collision avoidance, in dynamic unknown environments.
  • Dynamic Flow of Information: Pre-training from scratch and post-training with transfer learning of RGB-D encoders for downstream tasks, using CNNs, MLPs, transformers.
  • Testbed Environments (HIL): Train and test in high-fidelity simulators (AirSim, Unreal Engine) and deploy to real-world hardware via (NVIDIA Jetson, DJI Tello)
  • Data Collection: Generate real-world and simulated datasets connecting multimodal sensor observations, environments, optimal actions, and shortest paths (A*).
  • Map Building: Process spatio-temporal RGB-D sensors to refine 2D and 3D information, using ray tracing, updated occupancy grids, and casting to 3D point clouds.
  • Scaling Experiments: Build and routinely maintain AI-accelerated servers for distributed deep learning; streamline data processing via Python/Linux automation.
  • sim-to-real: I train models, especially DRL ones, and deploy to real-world drones.

Research Scientist | Lunar and Planetary Lab, University of Arizona (UoA) | Summer 2025

  • Multimodal Sensor Fusion: Architected an end-to-end pipeline in PyTorch integrating Raman spectra and images via data processing and CNN/MLP feature extractors for autonomous mineral classification onboard Martian and Lunar rovers.
  • Distributed Training: Leveraged HPC and SLURM to manage large-scale planetary datasets (20+ years of heterogeneous data), optimizing downstream tasks through transfer learning by utilizing frozen multi-stem networks and hyper-parameter searches.

Student Research Scientist | Scientific Data Division, Lawrence Berkeley National Laboratories (LBNL) | Summers 2023 – 2024

  • Probabilistic Modeling: Implemented Monte Carlo Dropout and sensitivity analysis with uncertainty quantification for interpretability in predictions, treatment of corrupted field data, and placement of sparse field sensors which are expensive and difficult to install.
  • Denoising Methods: Further gap-filled and reduced inherent noise in real-world data by utilizing dropout with implicit/explicit Denoising AutoEncoder (DAE) techniques.
  • Spatio-Temporal Modeling: Developed a U-Net framework to fuse satellite, weather and soil data, for large-scale watershed modeling and predicting evapotranspiration.
  • Distributed Training: Executed large-scale parallel processing through the National Energy Research Scientific Computing Center (NERSC) with SLURM and Python to accelerate big data processing, deep learning, and hyper-parameter optimization.

Intern Data Scientist | eHealth, Inc. | Summers 2020 – 2021

  • Recommender Systems: Integrated multi-branch feature extractors with downstream models used to recommend the top-N health insurance policies to live agents.
  • Data Science: Developed Graph Convolutional Networks (GCNs) and explainable ML to exploit relational structures in data and provide interpretable predictions, by accessing and processing data via SQL queries, AWS, DataBricks, and distributed computing.

Intern to Full-Time Research Scientist | NASA Ames & SETI Institute | 2015 – 2021

  • Systems Engineering:  Built a neural network from scratch in raw C++ to classify exoplanet spectra for satellite mission planning. Deployed a 2D traverse system using LabView and a Cobra probe for wind tunnel surveys. Engineered a web-crawler in Java to post-process aircraft flyover data in noise-mitigation studies. Pioneered preliminary work for my continued research at UoA above. This work was conducted in parallel to my undergraduate and initial graduate studies, taking full semesters off and a gap-year to work through part-time, full-time, grant-funded, and internship-based research.

EDUCATION

  • Ph.D. Computational Science | UCI, San Diego State University | expected June 2026
  • M.S. Data Analytics | San Jose State University | 2021
  • B.S. Applied Physics | University of California, Irvine | 2018

PUBLICATIONS (See Google Scholar for full list)

  • Johnsen, T. K., et al. “Denoising autoencoder for reconstructing sensor observation data and predicting evapotranspiration: Noisy and missing values repair and uncertainty quantification.” Water Resources Research, 2025.
  • Johnsen, T. K., et al. “Single and Multi-Mineral Classification using Dual-Band Raman Spectroscopy for Planetary Surface Missions.” American Mineralogist, 2025.
  • Johnsen, T. K., et al. “SmartDepth: Motion-Aware Depth Prediction with Intelligent Computing for Navigation.” IEEE, DCOSS-IoT, 2025.
  • Johnsen, T. K., et al. “An Overview of Adaptive Dynamic Deep Neural Networks via Slimmable and Gated Architectures.” IEEE, ICTC, 2024.
  • Johnsen, T. K., et al. “NaviSlim: Adaptive Context-Aware Navigation and Sensing via Dynamic Slimmable Networks.” IEEE, IoTDI, 2024.
  • Johnsen, T. K., et al. “NaviSplit: Dynamic Multi-Branch Split DNNs for Efficient Distributed Autonomous Navigation.” IEEE, WoWMoM, 2024.
  • Johnsen, T. K., et al. “A Multilayer Perceptron for Obtaining Quick Parameter Estimations of Cool Exoplanets from Geometric Albedo Spectra.” Publications of the Astronomical Society of the Pacific, 2020.
  • Johnsen, T. K., et al. “Elastic Net to Forecast COVID-19 Cases.” IEEE, 3ICT, 2020.

ADDITIONAL RESOURCES

Personal Website https://timkjohnsen.com/
LinkedIn https://www.linkedin.com/in/tim-johnsen/
Google Scholar https://scholar.google.com/citations?user=nvidNbAAAAAJ&hl=en
GitHub https://github.com/wreckittim