JD
Job Description: Generative AI Engineer (4?7 years)
Role Overview
We are seeking a highly skilled Generative AI Engineer with 4?7 years of professional experience to design, develop, and optimize GenAI solutions. The ideal candidate will have strong expertise in Retrieval-Augmented Generation (RAG) architecture, unstructured data processing, vector database management, and cloud-based data engineering using GCP technologies.
Key Responsibilities
– Design and implement RAG-based solutions by integrating LLMs with structured and unstructured datasets.
– Process and transform unstructured data from multiple file types (e.g., PPTX, DOCX, PDF) into usable formats for AI/ML workflows.
– Develop efficient data chunking, embedding, and indexing pipelines into vector databases for retrieval tasks.
– Build and optimize GenAI-based applications leveraging foundational AI/ML concepts.
– Write efficient and clean Python and SQL code to process, transform, and query data.
– Work with GCP services such as BigQuery, Dataflow, and Pub/Sub to build scalable data pipelines.
– Contribute to DevOps processes including CI/CD pipelines, automation, and deployment of AI/ML models.
– Collaborate with data scientists, engineers, and product teams to integrate AI into business applications.
– Explore and drive POCs around Graph Databases for relationship-based data retrieval (good-to-have).
Required Skills
– Strong understanding of RAG (Retrieval-Augmented Generation) architecture.
– Hands-on experience with data ingestion and processing of unstructured files (PPTX, DOCX, PDF).
– Practical experience in vector databases (e.g., Pinecone, Weaviate, FAISS, Milvus).
– Proficiency in Python for AI pipeline development and SQL for complex queries.
– Exposure to GCP services (BigQuery, Dataflow, GCS, Pub/Sub).
– Familiarity with DevOps processes such as CI/CD, containerization (Docker), and orchestration (Kubernetes).
– Strong problem-solving and debugging skills.
Nice-to-Have
– Knowledge of Graph Databases (e.g., Neo4j, TigerGraph).
– Experience contributing to end-to-end GenAI product deployment in production.
– Exposure to ML model fine-tuning and optimization for domain-specific use cases.
Education
– Bachelor?s or Master?s in Computer Science, or a related field.