Senior AI Engineer (Computer Vision)

At Avenga, we believe that human creativity empowers technology that matters. Operating globally, our 6000+ specialists provide a full spectrum of services, including business and tech advisory, enterprise solutions, CX, UX and Ul design, managed services, product development, and software development.

This is the job

We are looking for a Senior AI Engineer to join an innovative project focused on building intelligent systems that transform complex engineering documentation into structured knowledge and simulation-ready models.

The role involves working with LLMs, Knowledge Graphs, and Computer Vision, combining unstructured data (e.g., P&IDs, technical specifications) with real-time inputs to automate model generation and system understanding.

This is you

• Strong experience with Python, FastAPI, async programming, and Docker
• Hands-on experience with training object detection models like YOLO or Detectron2, including dataset annotation and end-to-end pipelines
• Understanding of shape and line detection for technical diagrams like P&IDs
• Strong experience with Knowledge Graphs using Neo4j or NetworkX, including graph traversal and transformation
• Strong experience with LangChain and LangGraph for multi-agent systems, self-healing mechanisms, and LLM-as-judge patterns
• Hands-on experience with LLMs like OpenAI, Anthropic, or Gemini
• Strong understanding of Agentic RAG, function calling, prompt design for code generation, and vector databases like Pinecone or Qdrant
• Ability to wrap third-party libraries as callable tools for LLM agents using Pydantic
• Ability to work independently in R&D environments with changing priorities and strong ownership mindset

• Train object detection models to extract shapes, lines, and symbols from P&IDs
• Construct Knowledge Graphs from detected elements and transform them into simulation-ready models
• Design multi-agent systems with LangGraph using supervisor/worker patterns, state management, and self-healing
• Build Agentic RAG pipelines for generating simulation code
• Wrap simulation libraries as callable tools for LLM agents with Pydantic validation
• Build FastAPI backends with async support and Docker
• Own end-to-end solutions from concept to working prototype in fast-paced R&D environment

At Avenga, everyone matters. We provide equal opportunities in recruitment, career development, and leadership, regardless of race, ethnicity, gender identity, sexual orientation, disability, age, religion, or any other characteristic. We are committed to fostering a work environment where our diverse community of employees, candidates, and business partners actively shapes our growth. By bringing together people from different backgrounds and experiences, we build a workplace where everyone feels free to be themselves while honoring the boundaries of others.