Posted on: 12/05/2026



Description :
- Secondary skills : Multi cloud experience (AWS)
Key Responsibilities :
- Develop robust, scalable GenAI solutions using Google Cloud's Vertex AI ecosystem (including Vertex AI Workbench, Feature Store, and MLOps tools).
- Implement advanced RAG techniques, including strategic chunking, semantic boundary detection, negative sampling, and retrieval quality optimization.
- Engineer and deploy multi-agent systems and autonomous AI solutions.
- Ensure the production readiness of all AI systems by designing and implementing multi-layered security, PII redaction, input/output guardrails (toxicity, bias mitigation, factuality checks), and audit logging.
- Establish A/B testing, human evaluation processes, and define standard RAG metrics (e.g., Precision@K, Recall@K) to measure and improve model performance.
- Collaborate with engineering teams to ensure seamless deployment and operational excellence in a cloud native environment.
Required Technical Skills & Experience :
- Expertise in Google Cloud Platform services (GCP) for AI, including Vertex AI, BigQuery, Dataflow, and Cloud Run/Kubernetes. Hands on exposure to using GCP services for storage, serverless-logic, search, transcription, and chat.
- Proven ability to design and operate RAG-at-scale.
- Experience in Integration with MCP
- Deep technical understanding of vector databases, dimensionality trade-offs, similarity metrics, and
advanced reranking strategies.
- Strong proficiency in Python, including modern AI/ML frameworks like LangChain, LangGraph, and/or CrewAI.
- Must be proficient with AI-assisted development tools like Cursor and have demonstrable experience integrating and programming with large language models such as Anthropic's Claude.
- Experience implementing MLOps best practices, CI/CD, and deployment automation.
- Excellent problem-solving skills, particularly for debugging issues across the RAG lifecycle (chunking, embeddings, retrieval, LLM response)
Did you find something suspicious?