Physical AI Engineer

7RD; Delhi; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

7RD is building the Counter Drone Swarm Stack with an EdgeAI module that runs autonomous mission planning, tracking, and navigation on the edge. We seek a Physical AI Engineer to turn research into reliable perception and autonomy software on real hardware.

The role covers data collection, model development, onboard optimization, and integration with drone software, simulation, and hardware testing. 3+ years in related fields is expected.

Qualifications

• Bachelor's degree or equivalent in Computer Science, Electronics, Robotics or related field.
• At least 3 years of hands on experience developing and evaluating computer vision or autonomy software.
• Experience deploying YOLO family detectors to embedded hardware.
• Knowledge of quantization and runtime profiling with measuring accuracy, latency, memory and hardware limits.
• Experience developing robotic or drone autonomy algorithms and sim/testing them.
• Familiarity with reinforcement learning concepts and training setups.
• Strong Python and C++ skills with embedded Linux and Yocto builds.
• Ability to debug across models, sensors, timing and onboard hardware.

Responsibilities

• Vision models: Develop, train, fine tune, and evaluate YOLO based object detection and tracking pipelines for drone imagery.
• Data and evaluation: Build labeling, augmentation, dataset versioning, error analysis and repeatable workflows.
• Model optimization: Apply quantization, pruning, and runtime profiling for edge hardware.
• Reinforcement learning: Design training environments, reward functions, observations, actions and evaluation.
• Maneuver algorithms: Develop planning, guidance, obstacle avoidance, trajectory generation and control support.
• Embedded deployment: Package inference services for embedded computers, including Yocto recipes and startup.
• System integration: Connect perception and autonomy modules with sensors, telemetry and autopilot interfaces.
• Simulation and testing: Run sim and hardware-in-the-loop tests, inject faults and compare results.
• Software delivery: Write Python and C++ code, automate tests and releases, review changes.
• Cross functional support: Work with firmware, hardware, controls and simulation engineers.

Skills

Python

C++

Embedded Linux

YOLO

PyTorch

Reinforcement Learning

Data Labeling

Git

Yocto

ROS2

Education

Bachelor's degree or equivalent in CS/engineering

Tools

ONNX Runtime

TensorRT

OpenVINO

TFLite

PyTorch

Git

CI/CD

Yocto-based builds

Job description

7RD is building the Counter Drone Swarm Stack, powered by our core product: an EdgeAI Module for drones, a neural chip based \"brain\" that runs autonomous mission planning, target tracking, and navigation entirely on the edge, with no cloud or GPS dependency.

Job Description

JOBDESCRIPTION

Physical AIEngineer

EdgeAI, Autonomy and Simulation

Location:

Employment Type:

Full Time

Experience Level:

3+ Years

Department:

Engineering / AI and Autonomy

RolePurpose

The engineerwill turn research and system requirements into perception and autonomysoftware that performs reliably on real hardware. The position requirespractical ownership from data collection and model development through onboardoptimization, integration with drone software, simulation, and controlledhardware testing.

KeyResponsibilities

• Vision models: Develop, train, fine tune, and evaluate YOLO based object detectionand tracking pipelines for drone imagery and video.
• Data and evaluation: Build labeling, augmentation, dataset versioning, error analysis, andrepeatable evaluation workflows across lighting, motion, altitude, andenvironmental conditions.
• Model optimization: Apply quantization, pruning, model conversion, and runtime profilingto meet latency, memory, compute, power, and thermal limits on target hardware.
• Reinforcement learning: Design training environments, reward functions, observations, actions,constraints, and evaluation procedures for autonomous behavior.
• Maneuver algorithms: Develop and test planning, guidance, obstacle avoidance, trajectorygeneration, and control support algorithms for complex maneuvers within definedsafety limits.
• Embedded deployment: Package inference services and supporting software for embeddedcomputers, including Yocto recipes, dependencies, startup, logging,configuration, and updates.
• System integration: Connect perception and autonomy modules with sensors, camera streams,telemetry, navigation estimates, autopilot interfaces, and ground tools.
• Simulation and testing: Set up realistic scenarios, run software in the loop and hardware inthe loop tests, inject faults and edge cases, and compare simulated performancewith recorded or physical tests.
• Software delivery: Write maintainable Python and C++ code, review changes, automate testsand builds, document design decisions, and produce reproducible releases.
• Cross functional support: Work with firmware, hardware, controls, andsimulation engineers to define interfaces, review risks, reproduce issues, andsupport controlled field trials.

CoreTechnical Areas

Area

Expected Knowledge andApplication

YOLO training and inference, detectionmetrics, tracking, camera geometry, preprocessing, image quality, and failureanalysis.

Machine learning

PyTorch or a comparable framework, datasetmanagement, experiment tracking, generalization checks, and reproducibletraining.

Edge optimization

INT8 or mixed precision quantization,calibration, operator support, model export, profiling, and accuracy versuslatency tradeoffs.

Policies, environments, reward design,exploration, constraints, offline evaluation, and transfer from simulation tohardware.

Autonomy algorithms

State estimation inputs, path and trajectoryplanning, collision avoidance, maneuver constraints, guidance logic, andautopilot integration.

Embedded Linux

Yocto recipes and images, cross compilation,services, containers or packages where appropriate, device access, logs, anddeployment.

Simulation and test

Scenario design, sensor and dynamics models,software in the loop, hardware in the loop, regression tests, telemetryreplay, and performance measurement.

Software engineering

Python and C++, Git, code review, unit andintegration tests, CI, clear interfaces, observability, and releasedocumentation.

Requirements

RequiredQualifications

• Bachelor's degree or equivalent practicalexperience in Computer Science, Electronics, Robotics, Aerospace Engineering,or a closely related discipline.
• At least 3 years of hands on experiencedeveloping and evaluating computer vision or autonomy software, including aYOLO family detector deployed to embedded hardware.
• Practical knowledge of quantization and runtimeprofiling, with evidence of measuring model accuracy, latency, memory use, andhardware resource limits.
• Experience developing algorithms for roboticor drone autonomy and testing them in simulation.
• Working knowledge of reinforcement learningconcepts and the ability to define meaningful training and evaluation setups.
• Strong Python skills, working C++ skills, andexperience integrating software on embedded Linux, including Yocto basedbuilds.
• Ability to debug across models, software,sensors, system timing, and onboard hardware using logs and repeatable tests.

PreferredExperience

• Experience with ArduPilot or PX4, MAVLink, ROS2, camera and IMU data, GNSS, and telemetry pipelines.
• Deployment with ONNX, TensorRT, OpenVINO,TFLite, or hardware specific inference runtimes and accelerators.
• Synthetic data generation, domainrandomization, visual simulation, and methods for reducing the gap betweensimulation and field performance.
• Development of software in the loop orhardware in the loop test benches, automated scenario suites, and telemetryreplay tools.
• Experience with real time constraints, faulthandling, safe behavior when perception is uncertain, and controlled fieldvalidation.
• AI or autonomy development for defence,aerospace, robotics, industrial automation, or other reliability sensitivesystems.