Senior AI/ML Engineer/AI Application Engineer

Tasks

• Design and develop AI agents using Python 3.12, LangChain, LangGraph, and Strands.
• Build multi-agent orchestration and domain-specific AI solutions.
• Integrate LLMs and foundation models for reasoning, tool calling, and workflow automation.
• Deploy AI agents using Amazon Bedrock AgentCore Runtime and Azure OpenAI.
• Implement agent-to-agent communication using A2A 1.0 and Python a2a-sdk.
• Develop secure agent-to-tool integrations using MCP and Amazon Bedrock AgentCore Gateway.
• Work with PostgreSQL, Amazon S3, and AWS Secrets Manager.
• Implement monitoring, logging, and distributed tracing using OpenTelemetry and Amazon CloudWatch.
• Develop unit, integration, and contract tests using pytest.
• Build scalable, secure, and reliable enterprise AI applications.

Requirements

• Strong Python 3.12 programming and asynchronous programming.
• Hands-on experience with LangChain, LangGraph, or Strands.
• Experience with LLMs, Foundation Models, Prompt Engineering, and Tool Calling.
• Strong AWS Cloud Services experience.
• Knowledge of REST APIs, PostgreSQL, and distributed systems.
• Experience with multi-agent orchestration and enterprise AI integrations.
• Understanding of structured outputs, context management, and LLM response validation.
• Preferred: Amazon Bedrock AgentCore Runtime, Gateway, and Observability.
• Preferred: Agent-to-Agent (A2A) protocols and Model Context Protocol (MCP).
• Preferred: AWS S3, Secrets Manager, and CloudWatch.
• Preferred: OpenTelemetry, HashiCorp, and pytest.
• Preferred: Docker, Kubernetes, and CI/CD pipelines.
• Preferred: Retrieval-Augmented Generation (RAG), LLM evaluation, and AI Guardrails.
• Preferred: Experience deploying production-grade AI applications.

Schedule

• Full-Time
• Onsite

How to apply

• Share your updated resume by email.

Location

• Atlanta, GA