Robosim AI
Python Full Stack Developer - Video analytics expertise
We are looking for a skilled Python Developer with a strong focus on Video Analytics to join our core engineering team. In this role, you will build and scale the backend infrastructure that ingests, processes, and analyzes live CCTV video streams. You will work closely with Computer Vision engineers to deploy deep learning models into production, ensuring low-latency inference and high throughput.If you are passionate about video codecs, streaming protocols, and optimizing Python for high-performance computing, we want to hear from you.Key Responsibilities
Video Pipeline Development: Design and implement scalable video ingestion pipelines using protocols like RTSP, RTMP, HLS, and WebRTC.
AI Integration: Deploy and optimize Computer Vision models (Object Detection, Tracking, Facial Recognition) into the production environment using Python.
Performance Optimization: Optimize code for latency and throughput; manage multi-threading, multiprocessing, and async I/O to handle multiple video streams simultaneously.
Backend Services: Build robust RESTful or gRPC APIs using FastAPI/Django to serve analytics data to frontend dashboards and third-party integrations.
Data Management: Architect database solutions to store video metadata, alerts, and events (Time-series and Relational DBs).
Infrastructure: Containerize applications using Docker and orchestrate deployments via Kubernetes (K8s) across cloud and edge environments.
Collaboration: Work with ML researchers to convert models (PyTorch/TensorFlow) to inference-optimized formats (ONNX, TensorRT, OpenVINO).
Required Skills & Qualifications
Education: Bachelor's or Master's degree in Computer Science, Engineering, or related field.
Python Expertise: 3+ years of strong proficiency in Python (3.8+), including async programming (asyncio), generators, and memory management.
Video Processing: Hands-on experience with OpenCV, FFmpeg, or GStreamer. Understanding of codecs (H.264, H.265) and container formats.
Deep Learning Frameworks: Familiarity with PyTorch or TensorFlow. Experience deploying models using ONNX Runtime, NVIDIA TensorRT, or OpenVINO is highly desirable.
Web Frameworks: Proficiency in building APIs with FastAPI, Flask, or Django.
Databases: Experience with PostgreSQL, Redis (caching), and Time-series databases (InfluxDB, TimescaleDB) for storing analytics events.
System Design: Strong understanding of message queues (Kafka, RabbitMQ, AWS Kinesis) for decoupling video processing tasks.
DevOps: Experience with Docker, CI/CD pipelines, and Linux environment management.
Preferred (Nice-to-Have) Skills
Experience with Edge Computing devices (NVIDIA Jetson, Raspberry Pi, Intel NUC).
Knowledge of cloud video services (AWS Kinesis Video Streams, Azure Video Analyzer, Google Cloud Video AI).
Familiarity with C++ for creating Python bindings to optimize performance-critical modules.
Experience with specific analytics use cases: License Plate Recognition (ALPR), People Counting, Loitering Detection, or PPE Detection.
Knowledge of security standards (GDPR, HIPAA) regarding video data privacy.
Soft Skills
Strong problem-solving skills with a focus on debugging complex streaming issues.
Ability to translate business requirements into technical specifications.
Excellent communication skills to collaborate with cross-functional teams.
Adaptability to work in a fast-paced, evolving technology landscape.
Please submit your Resume and a link to your GitHub/Portfolio.
Note: Candidates with public repositories demonstrating video processing or CV projects will be prioritized.
