Role Overview
We are looking for a hands-on AI Engineer with strong Python and LLM integration experience to build and deploy production-ready AI systems.
Responsibilities
- Develop real-time video processing systems using OpenCV.
- Implement object detection and tracking using YOLO or similar models.
- Build scalable APIs using FastAPI.
- Integrate AI/LLM services such as Google Gemini/OpenAI.
- Design and implement RAG pipelines.
- Work with MySQL/PostgreSQL and Hugging Face models/tools.
- Optimize AI models and pipelines for real-time performance.
- Collaborate with React/Angular frontend teams.
- Debug, test, and deploy scalable AI solutions.
Requirements
- Strong proficiency in Python and API development (FastAPI/Flask/Django).
- Hands-on experience with OpenCV and YOLO/object detection.
- Experience with LLM integration (Gemini/OpenAI or similar).
- Understanding of prompt engineering and RAG pipelines.
- Good knowledge of MySQL/PostgreSQL.
- Strong problem-solving and debugging skills.
- Ability to build end-to-end systems with minimal guidance.
Skills
- Python
- OpenCV
- FastAPI
- YOLO
- LLM
Nice to Have
- RTSP video streams and real-time processing.
- Vector databases (FAISS, Pinecone, Weaviate).
- Docker and basic DevOps.
- Async programming and WebSockets/real-time systems.
- AWS/GCP/Azure exposure.