SLAM & Computer Vision Engineer - BIM

Job Title : SLAM & Computer Vision Engineer

Experience Required : 4 - 8 Years Experience

Job Location : Mumbai / Pune

Education : B.Tech / M.Tech in Computer Science, Electronics, Robotics, Vision AI, or a related engineering discipline

ABOUT US :

Technosoft Engineering Solutions is building an AI-powered visual intelligence platform for the Indian construction industry. We bridge the gap between what is planned (BIM models, 2D drawings) and what is built on site, using real-time visual intelligence and spatial computing.

We are a product-first team working on hard engineering problems. This is a high-ownership, greenfield role with direct impact on product.

THE ROLE :

We are looking for a SLAM & Computer Vision Engineer to own the indoor positioning, spatial mapping, BIM alignment, and site capture pipeline within our platform.

You will design the core technical architecture for these areas and work alongside cloud and mobile developers to develop a complete solution. Your responsibility is the spatial intelligence engine - SLAM, sensor fusion, BIM geometry processing, metadata enrichment - and ensuring it integrates cleanly into the mobile and backend stack.

This is a production engineering role. We need someone who ships systems that work reliably in real-world, physically demanding environments - not just research prototypes.

WHAT WE ARE LOOKING FOR :

SLAM & Indoor Localisation (Core Requirement) :

- Hands-on experience building SLAM systems in production : EKF-SLAM, FastSLAM, ORB-SLAM, RTABMap, Cartographer, or equivalent

- IMU sensor fusion : accelerometer, gyroscope, magnetometer for real-time pose and position estimation

- Kalman filtering (EKF/UKF), particle filters, or graph-based optimization (g2o, GTSAM) for drift management and loop closure

- Experience deploying SLAM in real-world, noisy, GPS-denied environments

- Familiarity with ROS is a plus

3D Geometry & Spatial Computing (Core Requirement) :

- Strong grasp of 3D coordinate transformations, quaternions, and rotation matrices

- Experience with OpenCV, PCL (Point Cloud Library), or Open3D

- Ability to implement spatial queries against 3D geometry proximity detection, bounding box intersection, coordinate space conversions

- Experience with Structure-from-Motion (SfM) or Visual-Inertial Odometry is a strong plus

BIM & CAD Data Processing (Good to Have) :

- Experience parsing IFC files (IFC 2x3 / IFC 4) using IFC Open Shell or similar libraries

- Extracting element geometry, properties, and spatial relationships from BIM models across LOD 200-400

- Working with DWG/DXF CAD formats and floor plan coordinate systems

- Knowledge of Autodesk Revit or Navisworks workflows is a plus

Mobile Integration :

- Ability to design the SLAM and spatial engine as a modular component that integrates into an Android application built by a dedicated mobile developer

- Experience defining clear interfaces (APIs, SDKs, or native libraries) between a spatial computing engine and a mobile application layer

- Familiarity with Android NDK and how native C/C++ modules interface with the Android app layer (JNI) is required

- Understanding of mobile constraints : battery, memory, offline storage, and connectivity to design components that respect these limits

Backend & API Development :

- Designing and building RESTful APIs

- API documentation using OpenAPI 3.0 / Swagger

- Experience with chunked and resumable upload patterns for large video files

- Cloud deployment on AWS (S3, EC2, Lambda)

Programming Languages :

- C++ - strong proficiency (SLAM engine, performance-critical spatial code)

- Python - proficient (backend, data pipelines, scripting)

- SQL - comfortable with schema design and queries

Video Streaming & Media Handling :

- Familiarity with H.264 / H.265 video formats

- Frame extraction, thumbnail generation, and JSON metadata sidecar patterns

- Experience with FFmpeg is a plus

QUALIFICATIONS :

- 4-8 years of professional software engineering experience

- Minimum 2 years building SLAM, localisation, or spatial computing system

Skills

Visual SLAM, Computer Vision, 3D, OpenCV, CAD, C++, Python, Data Science, Deep Learning, Machine Learning