Platform Engineer III

Job description

Platform Engineer III India Platform Engineer III Chennai, Tamil Nadu Job Summary Implement generative AI models on AWS, identify insights that can be used to drive business decisions. Work closely with multi-functional teams to understand business problems, develop hypotheses, and test those hypotheses with data, collaborating with cross-functional teams to define AI project requirements and objectives, ensuring alignment with overall business goals. Optimizing existing generative AI models on AWS for improved performance, scalability, and efficiency. -Ensure data quality and accuracy -Implement NLP techniques and prompt engineering methodologies to enhance the capabilities and efficiency of GenAI models. -Experience working with cloud based platforms (AWS preferred) -Strong problem-solving and analytical skills. Experience on Multi Agent Systems, Multi Agent Orchestration is desirable AI DevOps & ML Ops: Deep expertise in developing, testing, deploying, and monitoring AI applications and infrastructure using Git and robust CI/CD pipelines. AWS Agentic Workflows: Experience using AWS Bedrock and Agent Core to build AI agents that can reason and execute tasks. Strong Coding: Proficiency in Python and Node.js for backend development and API integration. Technical Stack Requirements AI & ML: PyTorch, Multi Agent Systems, LangChain, Amazon Bedrock, RAG, Natural Language Processing, LLMops, ML Pipelines, Generative AI: Amazon Bedrock (Agents, Knowledge Bases, Guardrails), Agent Core. Cloud Platform: AWS (Lambda, API Gateway, S3, IAM, CloudWatch/X-Ray for Monitoring). Programming Languages: Python (Primary), Node.js. DevOps & Tools: Git, CI/CD (Deep Experience with GitHub Actions / AWS CodePipeline), Terraform or CloudFormation (IaC), Artifact Management. Integration Standards: REST APIs, OData, OpenAPI (Swagger) Specifications, JSON. Key Responsibilities Implement generative AI models on AWS, identify insights that can be used to drive business decisions. Work closely with multi-functional teams to understand business problems, develop hypotheses, and test those hypotheses with data, collaborating with cross-functional teams to define AI project requirements and objectives, ensuring alignment with overall business goals. Optimizing existing generative AI models on AWS for improved performance, scalability, and efficiency. -Ensure data quality and accuracy -Implement NLP techniques and prompt engineering methodologies to enhance the capabilities and efficiency of GenAI models. -Experience working with cloud based platforms (AWS preferred) -Strong problem-solving and analytical skills. Experience on Multi Agent Systems, Multi Agent Orchestration is desirable AI DevOps & ML Ops: Deep expertise in developing, testing, deploying, and monitoring AI applications and infrastructure using Git and robust CI/CD pipelines. AWS Agentic Workflows: Experience using AWS Bedrock and Agent Core to build AI agents that can reason and execute tasks. Strong Coding: Proficiency in Python and Node.js for backend development and API integration. Skill Requirements Technical Stack Requirements AI & ML: PyTorch, Multi Agent Systems, LangChain, Amazon Bedrock, RAG, Natural Language Processing, LLMops, ML Pipelines, Generative AI: Amazon Bedrock (Agents, Knowledge Bases, Guardrails), Agent Core. Cloud Platform: AWS (Lambda, API Gateway, S3, IAM, CloudWatch/X-Ray for Monitoring). Programming Languages: Python (Primary), Node.js. DevOps & Tools: Git, CI/CD (Deep Experience with GitHub Actions / AWS CodePipeline), Terraform or CloudFormation (IaC), Artifact Management. Integration Standards: REST APIs, OData, OpenAPI (Swagger) Specifications, JSON. Other Requirements null