Generative AI & Computer Vision Engineer
🔍 About Me
- 6+ years of experience designing and deploying end-to-end AI solutions across pharmaceutical, smart city, industrial, and security domains.
- Specialized in Generative AI (LLMs, VLMs, Diffusion Models) and Computer Vision, with expertise in RAG systems, multi-agent apps, and orchestration frameworks (AutoGen, CrewAI, LangGraph).
- Skilled in translating complex business requirements into practical, production-ready AI systems deployed on AWS, GCP, and Azure.
💡 What I Do
- Build GenAI-powered assistants and automation tools, such as document assistants for pharma teams and content compliance-checking systems.
- Apply text, image, and video generation models to create domain-specific applications that are compliance-friendly and reduce reliance on external vendors.
- Design scalable inference pipelines with Docker, FastAPI, Triton, and integrate real-time architectures with WebSockets, Celery, and AWS SQS/RabbitMQ.
- Deploy and manage AI workloads using ECS, Vertex AI, and Azure AI Foundry, ensuring strong MLOps practices (lifecycle, versioning, monitoring).
📚 Skills
- Programming: Python, C++, SQL, Bash
- Generative AI: LLMs, VLMs, Diffusion Models, Multi-Agent Systems (AutoGen, CrewAI, LangGraph), RAG Architectures, Prompt Engineering, LLM Evaluation (TruLens, Guardrails)
- Computer Vision: OCR, Object Detection, Image/Video Processing, Classical Vision (Contours, K-Means)
- APIs & Microservices: FastAPI, REST, WebSockets, Uvicorn, Celery
- Frameworks/Libraries: PyTorch, TensorFlow, Keras, OpenCV, scikit-learn, NumPy, Pandas, MatPlotLib, Kafka, Kubernetes, Git
- DevOps & Cloud: Docker, Kubernetes, Jenkins, AWS (ECS, SQS, ECR), GCP (Vertex AI, Vector Search), Azure (AI Foundry, ML Studio)
🎓 Relevant Coursework
- Computer Vision Nanodegree (Udacity)
- Deep Learning Specialization (Coursera)
📫 Get in Touch
- LinkedIn: Ishant Bansal
- Email: [email protected]