AI/ML Engineer

NeuBodhi; Pune District; On-site; INR 600,000 - 1,200,000; Full time

Job summary

NeuBodhi seeks an AI/robotics engineer to build perception, sensor fusion, and navigation models for autonomous platforms. You will deploy on NVIDIA Jetson and contribute to SLAM, ROS 2, simulation, and LLM applications.

Responsibilities include developing perception pipelines, sensor fusion, localization, mapping, and edge deployment of ML models with tools like PyTorch, TensorRT, and ONNX. Collaboration across robotics and software teams is essential.

Qualifications

• B.E./B.Tech/M.Tech in CS/IT/AI or related field.
• 1-2 years hands-on experience in ML/AI development.
• Strong Python and C++ programming skills.
• Experience with PyTorch or TensorFlow and computer vision models.
• Understanding of CV fundamentals: camera models, calibration, and coordinate transforms.
• Experience deploying ML models to production or edge devices.
• Familiarity with Linux, Git, Docker, and REST APIs.
• Willingness for field deployments and data collection.

Responsibilities

• Develop perception pipelines for object detection, segmentation, tracking, and classification using multi-sensor data.
• Build sensor fusion and state estimation with Kalman filters and Bayesian fusion.
• Contribute to localisation, mapping, path planning, and ROS 2-based systems.
• Work on SLAM and VO solutions for GPS-denied navigation.
• Optimize ML models for edge devices like NVIDIA Jetson using TensorRT/ONNX.
• Build data pipelines, labelling workflows, and training infrastructure.
• Track experiments, version models/datasets, and monitor performance.
• Develop LLM applications, RAG pipelines, and agentic AI workflows for applied AI use cases.

Skills

Python

C++

Linux

Git

Docker

ROS 2

NVIDIA Jetson

TensorRT

ONNX

PyTorch

TensorFlow

OpenCV

YOLO

Transformers

Gazebo

CARLA

PCL

LiDAR

Radar

Education

B.E./B.Tech/M.Tech in CS/IT/EE/AI or related field

Tools

PyTorch

TensorFlow

OpenCV

YOLO

ROS 2

Gazebo

Isaac Sim

CARLA

NVIDIA Jetson

TensorRT

ONNX

Job description

Build perception, sensor fusion, and navigation models for autonomous vessels and ground robots. Deploy computer vision and edge AI on NVIDIA Jetson, and contribute to SLAM, ROS 2, simulation, and LLM applications through field trials and deployment.

Key Responsibilities

• Develop perception pipelines for object detection, segmentation, tracking, and classification using camera, thermal, radar, and LiDAR data
• Build sensor fusion and state estimation systems using Kalman filters, Bayesian fusion, and multi-target tracking techniques
• Contribute to localisation, mapping, path planning, and collision avoidance systems using ROS 2
• Work on SLAM and visual-inertial odometry solutions for GPS-denied navigation
• Optimize and deploy machine learning models on edge hardware such as NVIDIA Jetson using TensorRT, ONNX, and model quantization
• Build data pipelines, data labelling workflows, model training infrastructure, and evaluation frameworks
• Track experiments, version models and datasets, and monitor model performance after deployment
• Build LLM applications, RAG pipelines, and agentic AI workflows for applied AI use cases including offline and air-gapped environments
• Develop AI features for digital twins, predictive maintenance, anomaly detection, and decision-support systems
• Work with time-series, tabular, geospatial, and other structured and unstructured datasets as required by projects
• Use simulation environments such as Gazebo, Isaac Sim, Unity-based tools, and CARLA for system testing and synthetic data generation
• Participate in field trials to collect real-world data and validate AI and autonomous systems
• Collaborate with robotics, embedded, mechanical, and software engineering teams to integrate AI models into autonomous platforms

Candidate Requirements

• B.E./B.Tech/M.Tech degree in Computer Science, Information Technology, E&TC, AI/ML, or a related engineering field
• 1-2 years of hands-on experience in machine learning and AI development
• Strong programming skills in Python and working knowledge of C++
• Strong understanding of machine learning and deep learning fundamentals, linear algebra, probability, and statistics
• Hands-on experience with PyTorch or TensorFlow and modern computer vision models such as YOLO, transformers, and segmentation models
• Understanding of computer vision fundamentals including camera models, camera calibration, and coordinate transformations
• Experience deploying at least one machine learning model to production or an edge device
• Understanding of computer vision, object detection, image segmentation, object tracking, and model evaluation
• Comfortable working with Linux, Git, Docker, and REST APIs
• Strong problem-solving, analytical, communication, collaboration, and teamwork skills
• Willingness to work on field deployments, system validation, data collection, and troubleshooting
• Indian nationality required; background verification may apply for defence-related projects
• Python / C++
• PyTorch / TensorFlow
• OpenCV / YOLO / Transformers
• NVIDIA Jetson / TensorRT / ONNX
• Open3D / PCL / LiDAR / Radar
• LangChain / LangGraph