Senior Software Engineer - AI/ML Engineer AWS

Serve as a Senior AI/ML Engineer for agent-based initiatives, including scoping, estimation, and architectural design of AI & Business Applications.
. Design, develop, and deploy intelligent agents using AWS Bedrock, LangChain, Kiro, Graph DB, Strands, and related agent frameworks.
. Build and maintain applications using AWS agent core framework, orchestration layers, and hierarchical agent workflows to support complex reasoning and automation use cases.
. Develop secure, scalable APIs using AWS Lambda and API Gateway to expose AI and agent capabilities to downstream systems.
. Implement prompt engineering best practices to optimize model performance, accuracy, and reliability across use cases.
. Design and implement RAG (Retrieval Augmented Generation) pipelines leveraging vector databases and knowledge graphs.
. Monitor, evaluate, and optimize LLM performance, cost, latency, and reliability in production environments.
. Support testing cycles by validating AI outputs, identifying gaps, and improving agent behavior through tuning and iteration.
. Ensure solutions meet enterprise standards for security, compliance, and responsible AI usage.
Strong experience with Python & Spark for building AI, data, and agent-based applications.
. Hands-on experience with AWS Bedrock and large language models (LLMs).
. Experience using LangChain, Strands, or similar agent frameworks.
. Strong understanding of agent core design, multi-agent systems, and orchestration patterns.
. Experience building serverless solutions using AWS Lambda and API Gateway.
. Solid knowledge of prompt & context engineering techniques and LLM optimization strategies.
. Experience integrating LLMs with enterprise systems via APIs.
. Build Solutions to any complex business problem using AI-Development Life Cycle methodology.
. Strong problem-solving, communication, and collaboration skills.

Required qualifications to be successful in this role:

Must-Have Skills:

. 6+ years of experience in AWS business applications.
. . Experience with broader AI and agent frameworks, including hierarchical agents and autonomous agent architectures.
. . Familiarity with Model Context Protocol (MCP) and emerging agent interoperability standards.
. . Experience with Kiro or similar AI IDE tools for agent-assisted development workflows.
. . Experience with CI/CD pipelines, Infrastructure as Code (CDK, CloudFormation, or Terraform), and version control (Git).
. . Familiarity with containerization technologies such as Docker, Amazon ECS, or EKS for production AI deployments.
. . Experience with AWS Quick Tools and AWS Frontier Agents.
. . Hands-on experience with deep research agents and multi-step reasoning workflows.
. . Experience implementing RAG using Vector Databases (e.g., OpenSearch, Pinecone, FAISS) and Graph Databases.
. . Exposure to model tuning, embeddings, and evaluation techniques.
. . Knowledge of enterprise AI governance, security, and responsible AI practices.