.png){kind=logo}
Rahul Mangalampalli
Mid-level AI Software Engineer specializing in computer vision and multimodal systems
Connect with Rahul
Rahul already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
Robotics/perception engineer focused on production-grade, real-time systems—optimized self-supervised segmentation on Jetson Nano from ~6–10 FPS to ~20–25 FPS and scaled experimentation/deployment by unifying 15+ edge models in a modular PyTorch Lightning framework. Experienced integrating distributed LiDAR-camera fusion via gRPC/protobuf into mission planning, migrating ROS1→ROS2 Foxy for multi-drone perception, and adding Prometheus-based observability for long-running deployments.
Experience
Education
Key Strengths
- Edge deployment optimization: improved segmentation inference from ~6–10 FPS to ~20–25 FPS on Jetson Nano via profiling, layer fusion, TensorRT, and pipeline tuning
- Scalable ML/perception codebase refactoring: unified 15+ models into a modular PyTorch Lightning framework, cutting deployment time nearly in half
- Real-time robotics ML integration using decoupled, asynchronous interfaces (gRPC + protobuf) for distributed perception to mission planning
- ROS1→ROS2 Foxy migration for distributed multi-drone perception; built LiDAR-camera fusion nodes with synchronized outputs
- Production reliability architecture: process/container isolation with independent restarts; bounded-latency techniques (buffers, threading priorities, GPU pre-allocation)
- Operational observability: embedded Prometheus metrics in ROS2 nodes to track FPS/GPU and proactively find bottlenecks
Discover more candidates like Rahul
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent