Lead Software Engineer – Python, AI/Agent

Overview:

Leading AI-driven Global Supply Chain Solutions Software Product Company and one of Glassdoor’s “Best Places to Work”.

We are looking for a technically strong and hands-on Software Engineer with expertise in Python, AI/Agent development, FastAPI, Azure, and cloud-native microservices. The individual will contribute to building reliable, scalable, and secure AI-driven solutions while collaborating closely with engineering, product, and operations teams.

Scope:

The role involves designing, developing, and optimizing Python-based microservices and AI agent capabilities for the Supply Chain Data Platform. The incumbent will work on agent memory, tool/function calling, multi-step reasoning, RAG, prompt engineering, evaluation, observability, and cost optimization.

The role also involves contributing to technical design, troubleshooting production issues, improving service reliability, mentoring team members, and helping shape the roadmap for AI-driven capabilities.

Our current technical environment:

Software: Python, FastAPI, Git, REST API, OAuth, Snowflake

AI/Agent Architecture: AI Agents, RAG, Agent Memory, Tool/Function Calling, Multi-Agent Orchestration, Prompt Engineering, LLM Evaluation

Cloud & AI Platform: Microsoft Azure, OpenAI, Azure AI Foundry

Frameworks/Others: LangGraph, LangChain, AutoGen, CI/CD, Logging & Monitoring, Automated Testing.

What you’ll do:

• Develop high-quality software, including AI agent components and effective test code, following clean code principles and Blue Yonder standards.
• Design, build, and optimize Python-based microservices integrating AI agents into the Supply Chain Data Platform.
• Develop and fine-tune agent capabilities including memory management, tool/function calling, multi-step reasoning, RAG pipelines, and prompt engineering.
• Apply token optimization and cost-efficiency techniques for LLM-based solutions.
• Build evaluation frameworks to measure agent accuracy, reliability, and regression.
• Implement logging, monitoring, and observability for AI agent behavior in production.
• Contribute to scalable and reliable AI-driven application architecture.
• Translate business requirements into user stories and technical solutions for AI/agent-driven features.
• Lead the design of individual stories and translate designs into actionable development tasks.
• Participate in backlog grooming, planning, stand-ups, retrospectives, and code reviews.
• Triage, troubleshoot, and identify root causes of application and AI/LLM-related issues across environments.
• Work with operations teams to improve operational readiness and support the rollout of new AI-driven capabilities.
• Consider information security and responsible AI practices throughout development and code reviews.
• Stay current with emerging trends in AI agents, LLMs, RAG, and AI-assisted software development.
• Contribute to the team’s technical vision and roadmap for AI-driven capabilities.
• Mentor junior engineers and support onboarding and knowledge sharing.
• Drive automation and continuous improvement across development and operational processes.

What we are looking for:

• Bachelor’s degree in computer science, Engineering, or a related field with relevant software development experience.
• Strong hands-on experience with Python and FastAPI.
• Experience developing AI agents and LLM-based applications.
• Hands-on experience with agent frameworks such as LangGraph, LangChain, or AutoGen.
• Strong understanding of RAG, prompt engineering/prompt programming, agent memory, tool/function calling, and multi-agent orchestration.
• Experience with LLM evaluation, agent observability, logging, and monitoring.
• Experience with token optimization and LLM cost optimization.
• Strong experience developing REST APIs and microservices.
• Experience with Azure, OpenAI, and Azure AI Foundry.
• Experience with Snowflake, Git, OAuth, and cloud-native development.
• Strong understanding of clean code, testing, CI/CD, code reviews, and software engineering practices.
• Experience troubleshooting production issues and performing root-cause analysis.
• Good understanding of information security and responsible AI practices.
• Strong problem-solving, communication, collaboration, and mentoring skills.

Must Have Requirements:

Python, FastAPI, Git, REST API, OAuth, Snowflake Agent development frameworks (LangGraph, LangChain, AutoGen), Prompt Engineering, RAG, Agent Memory, Token/Cost Opt…