We are seeking a highly skilled MidSenior Level Engineer with strong expertise in Python, AWS cloud services, containerization, and modern AI/ML technologies. The ideal candidate has hands-on experience designing scalable data ingestion pipelines, deploying GenAI/LLM solutions, and building retrieval-augmented and agentic systems for enterprise use cases. This role involves end-to-end solution designdata, infrastructure, orchestration, and model integrationacross cloud-native environments. Key Responsibilities Design, develop, and deploy scalable applications and microservices using Python and AWS services (Lambda, ECS/EKS, S3, DynamoDB, API Gateway, Bedrock, CloudFormation, etc.). Build and maintain containerized workloads using Docker , GitHub workflows, and CI/CD automation. Develop robust data ingestion and processing pipelines integrating structured/unstructured data sources. Implement GenAI solutions using LLMs, embeddings, vector databases (Pinecone, FAISS, Redis, etc.) , and RAG architectures. Build and manage knowledge bases , embedding pipelines, and context-retrieval systems optimized for real-world performance. Design and orchestrate agentic workflows using modern agentic frameworks and multi-agent patterns for automation and decision-making. Work with AWS Bedrock to integrate foundation models, manage guardrails, tune prompts, and optimize model performance. Implement secure, scalable infrastructure using CloudFormation , IAM, VPC, and AWS networking best practices. Collaborate with cross-functional teams (data, product, engineering) to translate requirements into technical designs. Monitor, troubleshoot, and optimize production AI/ML workloads, including inference performance, latency, cost, and reliability. Maintain strong code quality standards through GitHub version control, documentation, and automated testing. Required Skills
Read Less
