Lead Perception Engineer
Leads development of real-time 3D perception and sensor-fusion systems for autonomous robots, covering localization, calibration, semantic scene understanding, and edge deployment. Requires 5+ years of experience, strong computer vision fundamentals, and proficiency in C++.
About the job
Responsibilities
3D Perception Development & Scene Understanding
- Design, implement, and deploy real-time 3D perception pipelines using LiDAR, IMU, stereo, and RGB cameras.
- Develop algorithms for spatial and temporal data interpretation to enable high-fidelity semantic scene understanding.
- Optimize ego-motion estimation and localization modules for integration with downstream planning and control tasks.
Deep Learning
- Train and integrate deep learning models for semantic world understanding and surface-finish classification for quality control.
- Collect and curate real and synthetic datasets.
- Automate training pipelines and experiment tracking.
- Benchmark and optimize perception models for edge devices and resource-constrained environments.
Sensor Fusion & Localization
- Design and implement sensor-fusion strategies combining visual, inertial, and spatial data.
- Integrate classical methods with deep-learning approaches to convert noisy, asynchronous data from heterogeneous sensors into a unified environment representation.
Calibration
- Develop and automate robust extrinsic and intrinsic calibration procedures for cameras, LiDAR, and IMUs using target-based and/or targetless methods.
- Design algorithms for online calibration-drift detection and self-healing during long-term deployments.
- Establish quantitative metrics to evaluate and certify calibration quality.
Collaboration
- Partner with Navigation, Manipulation, and Cloud teams to optimize perception outputs for path planning, grasping, and remote fleet monitoring.
- Define and track system-level and subsystem KPIs and perception metrics to identify regressions across software iterations.
Requirements
- 5+ years of professional experience.
- Strong fundamentals in computer vision and 3D perception.
- Proficiency in C++; Python is a plus.
- Familiarity with PyTorch and TensorRT.
- Basic understanding of localization and SLAM.
- Ability to work with real-world data and debug complex systems.
Nice-to-haves
- Experience with NVIDIA DeepStream, GStreamer, or Holoscan.
- Experience with ROS or ROS2.
- Hands-on experience with LiDAR, RGB-D cameras, or IMUs.
- Familiarity with OpenCV, PCL, or similar libraries.
- Experience working on robotics or vision-based projects.
Skills
C++, Python, Computer Vision, 3D Perception, Lidar, Imu, Stereo Cameras, Rgb Cameras, PyTorch, TensorRT, Slam, Ros2, Opencv, Pcl, Gstreamer
Similar jobs
ML Engineering jobs
GitLab
Bengaluru, India
Build and ship autonomous, agentic software development lifecycle capabilities, including AI agents, orchestration, and safety guardrails. The role requires senior software engineering experience, proficiency in Ruby, Go, or Python, distributed systems knowledge, and experience with AI/ML applications.
Airbnb
Bengaluru, India
Build and operate scalable AI/ML systems and pipelines that strengthen Airbnb’s fraud prevention and trust defenses. The role requires 7+ years of backend or platform engineering experience, strong programming and data engineering skills, and production machine learning expertise.
Together AI
Amsterdam, Netherlands
Build production AI agents and the distributed platform that operates large-scale GPU infrastructure. The role requires 5+ years of backend, distributed systems, or infrastructure experience, with expertise in agent systems, knowledge graphs, retrieval, or semantic search.
6sense
Bengaluru, India
Build and deploy explainable machine learning, NLP, LLM, and agentic systems that power enterprise go-to-market intelligence products. The role requires 6+ years of production ML experience, strong Python and cloud skills, and end-to-end ownership from modeling through monitoring.
Databricks
Bengaluru, India
Senior software engineer developing ML-based search relevance and discovery systems, including query understanding, ranking, retrieval, and evaluation pipelines. The role requires 5+ years of search relevance experience and expertise in NLP, LLMs, or related discovery technologies.