I
Jr. AI Engineer - INTL - India
Insight Global
2 hours ago
Full-time
On-site
East New York, New York, United States
Required Skills & Experience
• 0 to 1+ years of experience in software engineering, backend development, AI engineering, \nor a related role.\n• Hands-on experience with AWS cloud services, especially services used in modern AI \napplication development.\n• Good understanding of LLM-based applications, prompt engineering, and chatbot design.\n• Working knowledge of Node.js or TypeScript is a plus.\n• Experience integrating with REST APIs, JSON payloads, authentication flows, and \ndatabases.\n• Familiarity with Git, CI/CD, and software development best practices.
Nice to Have Skills & Experience • Experience with Amazon Bedrock for chatbot or GenAI use cases.\n• Experience with LangChain, LangGraph, CrewAI, or similar orchestration frameworks.\n• Exposure to multi-agent or agentic patterns.\n• Experience with vector databases or search platforms such as OpenSearch, Pinecone, \nFAISS, or similar.\n• Familiarity with serverless design patterns.\n• Exposure to cloud security, IAM, and monitoring fundamentals.\n• Experience automating business processes or internal workflows.
Job Description
We are seeking an AI Engineer with 0-2 years of experience to support the development of AI-powered applications, enterprise chatbots, and automation solutions within AWS. This role will focus on Retrieval-Augmented Generation (RAG), agent-based workflows, LLM integrations, and business process automation. The ideal candidate has a strong foundation in software engineering, cloud technologies, and modern AI application development.\n\nResponsibilities\n• Design, develop, and maintain AI applications using AWS services such as Amazon \nBedrock, Lambda, API Gateway, S3, DynamoDB, CloudWatch, and Step Functions.\n• Build enterprise chatbots and assistants using RAG over internal documents, knowledge \nbases, and business data.\n• Develop prompt workflows, tool-calling patterns, and simple agentic flows for task \nexecution.\n• Integrate AI applications with internal systems, databases, REST APIs, and third-party \nplatforms.\n• Support ingestion, chunking, embedding, retrieval, and grounding pipelines for knowledge\u0002based assistants.\n• Build backend services and orchestration logic using Python and/or Node.js.\n• Implement automation workflows for repetitive operational tasks, using AI where it adds \nvalue and standard automation where it is more appropriate.\n• Participate in prompt tuning, response evaluation, testing, debugging, and performance \nimprovement.\n• Implement logging, retries, error handling, and monitoring for deployed solutions.\n• Collaborate with business stakeholders, architects, and developers to convert use cases \ninto working AI solutions.
Nice to Have Skills & Experience • Experience with Amazon Bedrock for chatbot or GenAI use cases.\n• Experience with LangChain, LangGraph, CrewAI, or similar orchestration frameworks.\n• Exposure to multi-agent or agentic patterns.\n• Experience with vector databases or search platforms such as OpenSearch, Pinecone, \nFAISS, or similar.\n• Familiarity with serverless design patterns.\n• Exposure to cloud security, IAM, and monitoring fundamentals.\n• Experience automating business processes or internal workflows.
Job Description
We are seeking an AI Engineer with 0-2 years of experience to support the development of AI-powered applications, enterprise chatbots, and automation solutions within AWS. This role will focus on Retrieval-Augmented Generation (RAG), agent-based workflows, LLM integrations, and business process automation. The ideal candidate has a strong foundation in software engineering, cloud technologies, and modern AI application development.\n\nResponsibilities\n• Design, develop, and maintain AI applications using AWS services such as Amazon \nBedrock, Lambda, API Gateway, S3, DynamoDB, CloudWatch, and Step Functions.\n• Build enterprise chatbots and assistants using RAG over internal documents, knowledge \nbases, and business data.\n• Develop prompt workflows, tool-calling patterns, and simple agentic flows for task \nexecution.\n• Integrate AI applications with internal systems, databases, REST APIs, and third-party \nplatforms.\n• Support ingestion, chunking, embedding, retrieval, and grounding pipelines for knowledge\u0002based assistants.\n• Build backend services and orchestration logic using Python and/or Node.js.\n• Implement automation workflows for repetitive operational tasks, using AI where it adds \nvalue and standard automation where it is more appropriate.\n• Participate in prompt tuning, response evaluation, testing, debugging, and performance \nimprovement.\n• Implement logging, retries, error handling, and monitoring for deployed solutions.\n• Collaborate with business stakeholders, architects, and developers to convert use cases \ninto working AI solutions.