Job highlights

- Experience with AWS CDK Infrastructure as Code mandatory and CICD pipelines using CodePipeline CodeBuild CodeDeploy . Strong database expertise . RDSAurora PostgreSQLMySQL for transactional systems

Sr Developer AIML AWS MCP MultiAgent Python FastAPIFlaskDjango AWS LLMs Generative AI RAG AWS Bedrock Agentic AI MultiAgent Systems MCP Model Context Protocol SQL Vector Databases AWS CDK Strong experience designing and building agentic AI systems using multiagent architectures and MCPbased tool integration within AWS ecosystem Ability to translate requirements into scalable AI solutions using Bedrock Lambda Step Functions and eventdriven architectures Qualifications Develop pythonbased automation for large data sets data analysis for vulnerability management reporting Leverage machine learning in the process as required Develop Prompts to automate test data extraction process from databases Provide technical expertise through a handson approach to teams and projects Experience with one or more general purpose programming languages including but not limited to Java Python R or equivalent Experience and knowledge in designing building and deploying multi layered application Infrastructure involving Onpremises AWS Cloud platform using services BedRock LLM models Handle design definition planning and development 100 adherence to architectural and development best practices including the use of standard architectures proper use of code management document design and design artifacts and conduct designcode reviews





Create optimization plans to innovate shiftleft and mitigate gaps Apply cloud concepts and capabilities to deliver testing for cloudhosted apps Report succinct testing goals and results to the leadership Train and educate various teams on SV ideas and expectations Expand responsibilities to drive test data test environment and service virtualization strategies

Handson experience in Multiagent systems task orchestration planning execution tool usage mandatory MCP toolbased LLM integrations enabling agents to connect with APIs databases and enterprise systems mandatory

RAG pipelines including embedding generation chunking indexing retrieval optimization

Amazon Bedrock for LLMbased application development

Strong AWS experience building and deploying applications using

BedRock Lambda EC2 ECSFargate S3 VPC API Gateway RDS DynamoDB SQS SNS Step Functions EventBridge CloudFront ELB Auto Scaling Elastic Cache CloudWatch

Experience with AWS CDK Infrastructure as Code mandatory and CICD pipelines using CodePipeline CodeBuild CodeDeploy

Strong database expertise

RDSAurora PostgreSQLMySQL for transactional systems

DynamoDB for scalable NoSQL workloads

Vector Databases mandatory OpenSearch Pinecone Redis FAISS for embeddings and semantic search

Designing data models for AI applications including RAG pipelines and largescale unstructured data

Managing agent memory shortterm longterm using vector DB persistent storage Integrating databases with MCPbased tools for agentdriven data access 2 years of backendfull stack engineering experience and 1 years in Generative AI prompt engineering or AI system development Experience working in Agile environments building scalable microservices developing APIs and contributing to CICD pipelines Valuable understanding of SaaS PaaS IaaS cloud models and AWSfirst architecture Ability to build productiongrade AI systems not just PoCs with focus on scalability performance and maintainability

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 Specialist - Data Sciences (Kolkata)
🏢 LTM
📍 Kolkata