About the Role :

We are looking for an experienced Computer Vision AI Specialist / Multimodal AI Engineer to develop AI solutions for engineering and manufacturing use cases, with a strong focus on understanding and extracting information from engineering drawings and other visual technical documents.

Key Responsibilities :

- Design and develop computer vision and multimodal AI solutions for engineering drawings and technical documents.

- Build solutions for OCR, symbol detection, object detection, classification, image understanding, and information extraction from engineering drawings.

- Work with Vision Language Models (VLMs) to interpret visual and textual information from complex engineering documents.

- Develop Python-based AI applications, services, and processing pipelines for computer vision and multimodal use cases.

- Build RAG-based solutions for engineering drawing and technical-document retrieval and question answering.

- Develop pipelines for document processing, chunking, embeddings, metadata extraction, indexing, and semantic retrieval.

- Work with vector databases and retrieval architectures to enable efficient search across engineering drawings and associated documentation.

- Integrate foundation models and enterprise AI capabilities using AWS Bedrock and related services.

- Develop and deploy AI solutions using Databricks and cloud-native technologies.

- Design and implement multi-agent workflows for complex engineering and document-processing use cases.

- Work with MCP (Model Context Protocol) and related architectures to connect AI agents with enterprise tools, data, and services.

- Build scalable and secure AI applications using appropriate cloud and infrastructure patterns.

- Use Terraform for infrastructure provisioning and deployment automation.

- Evaluate model performance and improve accuracy, retrieval quality, latency, and reliability.

- Collaborate with engineering, manufacturing, product, and technology teams to translate business problems into scalable AI solutions.

- Develop technical documentation, conduct experimentation and proof-of-concepts, and support transition of solutions into production.

- Monitor and troubleshoot AI applications and continuously improve model and system performance.

Required Skills & Experience :

- 7 - 12 years of experience in AI/ML, Computer Vision, Multimodal AI, or related engineering roles.

- Strong hands-on experience in Computer Vision and multimodal AI.

- Experience working with engineering drawings, technical drawings, manufacturing documents, CAD-related data, or similar engineering content.

- Strong knowledge of OCR, object/symbol detection, image classification, document understanding, and visual information extraction.

- Hands-on experience with Vision Language Models (VLMs) and multimodal foundation models.

- Strong proficiency in Python for AI/ML application development.

- Experience building RAG pipelines, including embeddings, vector databases, semantic search, retrieval, and document processing.

- Experience with AWS Bedrock and enterprise GenAI services.

- Hands-on experience with Databricks and data/AI engineering workflows.

- Experience with Terraform and infrastructure-as-code practices.

- Strong understanding of LLM application architecture, prompt engineering, embeddings, and model evaluation.

- Experience designing or implementing agentic AI and multi-agent workflows.

- Understanding of MCP architecture and integrating AI agents with enterprise tools and data sources.

- Experience developing and deploying production-grade AI applications and APIs.

- Strong understanding of software engineering, version control, testing, deployment, and monitoring practices.

- Strong analytical and problem-solving skills with the ability to work on complex engineering and manufacturing use cases.

- Good communication and stakeholder management skills.