GenAI Engineer - W2 F2F

We are seeking a Senior GenAI Engineer with 9+ years of experience in building production-grade AI and data-driven applications. The role focuses on designing and developing Retrieval-Augmented Generation (RAG) systems, vector search architectures, and scalable GenAI-powered platforms using modern Python-based backend frameworks.

The ideal candidate combines strong backend engineering expertise with hands-on experience in advanced retrieval systems and real-world business use cases. Automotive domain knowledge in Sales, Services, Parts Pricing, and Warranty Claims is highly preferred.

• 1. GenAI Application Development
• Design and build scalable GenAI-powered applications using Python and FastAPI.
• Develop and deploy Retrieval-Augmented Generation pipelines using vector search and hybrid retrieval strategies.
• Integrate large language models with enterprise data sources.
• Implement evaluation frameworks to measure RAG accuracy, retrieval quality, and response relevance.
• Develop high-performance APIs using FastAPI.
• Implement data pipelines and orchestration workflows using Airflow and Astronomer.
• Build CI/CD workflows using Tekton.
• Design scalable search systems using Elastic Search and vector databases.
• 3. Retrieval & Search Architecture
• Design vector search architectures for structured and unstructured data.
• Implement embedding pipelines and similarity search strategies.
• Optimize search relevance, latency, and system performance.
• Evaluate and continuously improve RAG effectiveness.
• 4. Data & Workflow Orchestration
• Build ingestion, transformation, and inference pipelines.
• Manage DAG-based workflows using Airflow.
• Ensure reliability, scalability, and observability of AI systems.
• Translate Automotive Sales, Services, and Warranty business requirements into AI-driven solutions.
• Work closely with business stakeholders to optimize parts pricing and warranty claims workflows using AI.

• 9+ years of experience in software engineering and AI-driven application development.
• Strong proficiency in Python.
• Experience with FastAPI for backend services.
• Hands-on experience with RAG techniques and vector search implementations.
• Experience evaluating and tuning RAG systems.
• Expertise in Elastic Search.
• Experience with Airflow and Astronomer for workflow orchestration.
• Solid understanding of embedding models, similarity search, and retrieval optimization.
• Experience building production-grade APIs and distributed systems.