Description

You will design and implement scalable, fault-tolerant distributed systems using core Python and modern asynchronous frameworks. You will build AI agents that reason, plan, and act, implementing guardrails, ReAct patterns, and memory/tool-use capabilities like MCP. You will establish production-grade CI/CD, testing with pytest, and type safety with mypy to ensure code quality. You will also implement enterprise-grade security and compliance across cloud providers and data platforms.

This role is hybrid.

Responsibilities

• Design and implement distributed systems using Python, asyncio, and multithreading.
• Build AI agents and components with reasoning, planning, and tool-use capabilities.
• Establish production-grade CI/CD pipelines, testing (pytest), and type safety (mypy).
• Drive performance optimization through deep profiling and memory-aware engineering.
• Implement security, encryption, and secrets management across AWS, GCP, and Azure.

Required Skills

• Strong Python engineering with expertise in async, APIs, and microservices.
• Experience with AI agent frameworks such as LangChain or LangGraph.
• Proficiency in asyncio, multithreading, OOP, and memory management.
• Experience with cloud platforms: AWS, GCP, or Azure.
• Knowledge of data platforms like Snowflake or Databricks.
• Experience building and maintaining CI/CD pipelines.
• Bachelor's degree in a relevant field.
• 5+ years of professional experience.

Preferred Skills

• Experience with AIOps and Lakehouse architectures.
• Familiarity with prompt engineering collaboration.

Key Skills

Education

Bachelor's degree