Match Score
Against your primary resumeLogin to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Protocol Intelligence
Data-driven signals on your job's competitivenessLog in to see why each signal reads the way it does.
Job Description
Structured overview of role & requirementsAbout This Role
Design and develop AI agents capable of multi-step task execution, including multi-agent systems and agent workflows derived from business processes.
Build and maintain tools, integrations, and secure Model Context Protocol servers for agent operation, integrating with enterprise platforms like Salesforce and SAP.
Ensure reliability and safety of agents via evaluation suites, human-in-the-loop checkpoints, guardrails, traceability, cost and latency control, and deploy containerized agent services for client use and demos.
Minimum Requirements
Strong production-grade Python skills including typed, tested code and async programming.
Hands-on experience with LLM tool/function calling and structured outputs on major APIs (Anthropic, OpenAI, Google, or Azure OpenAI).
Built at least one working AI agent with frameworks like LangGraph, CrewAI, AutoGen, or OpenAI/Claude Agent SDKs.
Experience integrating REST APIs with authentication (OAuth, API keys, service accounts), testing agents with scenario-based tests, containerization with Docker, cloud deployment, and Git; work experience required: Not explicitly mentioned in the JD.
Ideal Candidate Profile
Experienced in AI agent design and orchestration with strong focus on operational reliability, evaluation, and integration with enterprise systems.
Proficient in building scalable, observable microservices including containerization and deployment in cloud environments.
Familiar with advanced AI frameworks, agent evaluation tools, Model Context Protocol, workflow and queue management, and enterprise platform integration.