AWS Bedrock & Generative AI Design and build GenAI solutions using AWS Bedrock and foundation models (FM) such as Amazon Titan, Anthropic Claude, etc. Implement LLM-based applications like chatbots, summarization engines, recommendation systems, and document intelligence Apply advanced prompt engineering, fine-tuning, and model evaluation techniques Design RAG (Retrieval-Augmented Generation) pipelines and integrate vector databases Python Development Develop scalable backend systems using Python (FastAPI, Flask, Django) Build APIs and microservices to integrate AI/ML services into business applications Write efficient scripts for data preprocessing, automation, and orchestration AWS Cloud & Architecture Design cloud-native solutions using AWS services (Lambda, API Gateway, S3, EC2, IAM, CloudWatch, Step Functions) Architect secure, scalable, and highly available systems Optimize cloud cost and performance Ensure data privacy and compliance for AI workloads Data & AI Integration Work with structured & unstructured datasets for AI applications Build pipelines to integrate external data sources with LLMs Implement vector search, embeddings, and semantic search capabilities Collaboration & Leadership Collaborate with data scientists, ML engineers, product teams, and business stakeholders Lead design discussions and provide technical guidance to junior developers Participate in Agile/Scrum development cycles
Additional Responsibilities:
Preferred Skills Experience with LangChain, LlamaIndex, or similar frameworks Knowledge of vector databases (FAISS, Pinecone, Weaviate, OpenSearch) Exposure to Docker, Kubernetes, and containerization Understanding of ML lifecycle, MLOps, and model deployment Experience in big data or data engineering tools (Glue, Redshift, Spark)
