Gen AI

Key Responsibilities
Design develop and deploy GenAI applications using Google Gemini or Amazon Bedrock Vertex AI or SageMaker Engineer and optimize prompts, pipelines, and LLM responses for scalable solutions Integrate GenAI capabilities into business applications via REST APIs, AWS Lambda, and cloud-native services Build and manage data pipelines using PostgreSQL for structured data access Implement Retrieval-Augmented Generation (RAG) architectures and vector search workflows Collaborate with cross-functional teams (ML engineers, product managers, IT, data teams) to gather requirements and deliver AI features Ensure reliability, scalability, and performance of deployed AI models Uphold secure, compliant, and ethical AI development practices Required Skills & Qualifications: Hands-on experience with Google Cloud Platform (GCP) services: Vertex AI, Cloud Functions, BigQuery, IAM or experience with Amazon Web Services (AWS) including Amazon Bedrock, SageMaker, Lambda, and IAM Experience working with Google Gemini or Amazon Bedrock, Anthropic Claude, Meta LLaMA, or other LLMs Proficiency in Python and ML/NLP libraries Transformers, LangChain, spaCy Strong knowledge of PostgreSQL for data querying and integration Familiarity with vector databases (e.g., FAISS, Pinecone, Amazon Kendra) and semantic search Understanding of prompt engineering, tokenization, and model fine-tuning Experience building REST APIs and integrating GenAI into applications Solid grasp of CI/CD practices and cloud-based deployment Preferred Qualifications GCP or AWS Certifications (e.g., Associate Cloud Engineer, Professional ML Engineer, AWS Certified Machine Learning Specialty) Experience with LangChain RAG pipelines, or similar frameworks Background in NLP deep learning or conversational AI Awareness of data privacy security and AI ethics principles