Blue Yonder

Software Engineer II- Python, LangGraph,OpenAI Agents SDK, RAG,LLM

Blue Yonder Hyderabad, Telangana, India

Software Development · 5,001-10,000 employees

Yesterday
python Mid (2-5 yrs) Full-time India
Create a free account to apply — email only, no card. You can also save this posting or score it against your profile with AI.

About the role

Design, implement, and maintain production-grade agent solutions using Python, LangGraph, and OpenAI Agents SDK. Collaborate with DevOps to manage CI/CD pipelines and participate in incident response and operational excellence.

What they look for

Python OpenAI Agents SDK LangGraph LangFuse RAG Prompt Engineering Context Engineering Multi-agent Orchestration CI/CD Mutation Testing Unit Testing Observability Retail Planning DevOps Agent Security Responsible AI

Requirements

Requires a degree in Engineering or MCA with 3 to 6 years of experience in agent development and Python. Strong proficiency in RAG, prompt engineering, and production-level agent orchestration is essential.

Full description

Scope:

We are seeking a hands-on Agent Engineer to design, build, and maintain production-grade agent solutions using Python using OpenAI Agents SDK, LangGraph, and LangFuse. The role focuses on feature delivery for multi-tenant services with strong tenant isolation, reliable CI/CD, rigorous automated testing (including mutation testing), and secure-by-default development practices. Delivers high-quality code, writes tests, participates in Agile ceremonies, collaborates with DevOps, and supports incident response and operational excellence.

 

Our current technical environment:

The engineer will be part of Retail planning agent team working alongside some of the senior architects and product managers and agent developers. Blue Yonder uses AI-driven Cognitive Solutions and agentic systems to turn fragmented supply chain data into real-time, global decisions. The role will play a key role in leveraging Blueyonder Agentic Platform to deliver solutions to our customers to push the frontier faster

 

What you’ll do:

Primary Responsibilities

  • Design, implement, and maintain production agent components in Python using OpenAI Agents SDK,LangGraph and LangFuse, following clean‑code principles and team standards.
  • Deliver features for multi‑tenant services with built‑in tenant isolation, baseline scalability, and secure defaults.
  • Produce clear, testable user stories and decompose work into subtasks with measurable acceptance criteria.
  • Write and maintain comprehensive unit tests and test automation; actively participate in mutation testing cycles and remediate identified gaps with guidance from senior engineers.
  • Collaborate in Agile ceremonies (backlog grooming, sprint planning, daily standups, retrospectives) and reliably deliver committed sprint work while surfacing risks early.
  • Work with DevOps to maintain and improve CI/CD pipelines: automate routine deployments, add relevant test stages, and troubleshoot build/test failures.
  • Participate in incident response and post‑mortem activities: provide technical analysis, implement remediation tasks, and document lessons learned.
  • Incorporate information‑security and data‑privacy best practices in design, implementation, and code reviews.
  • Monitor and improve observability: add meaningful metrics, logs, and traces to support debugging and operational visibility.
  • Keep up to date with agent development patterns, testing techniques, and observability tooling and propose practical improvements for the team.

Secondary Responsibilities

  • Provide constructive code review feedback and incorporate reviewer suggestions to raise code quality and consistency.
  • Produce and maintain onboarding documentation, runbooks, and troubleshooting guides to accelerate new team members and reduce operational friction.
  • Identify and implement small refactors and focused performance improvements; escalate larger refactor or architectural changes for team prioritization.
  • Help maintain CI/CD health: fix broken builds, add automation for linting and tests, and improve pipeline reliability.
  • Participate in technical interviews and candidate evaluations on request.
  • Assist with benchmarking and profiling tasks and implement remediation under supervision.
  • Ensure your work aligns with the team vision and communicate impediments that could block delivery.

What we are looking for:

  • BE/B. Tech or ME/M. Tech or MCA with 3 to 6 years of experience
  • Proficient with Python, OpenAI Agents SDK, RAG, Prompt Engineering, Context Engineering
  • Experience in benchmarking Evaluation sets, writing evaluators.
  • Multi Agent Orchestration- Worker (Supervisor), Concurrent (Fan-Out/Fan-In) etc
  • Skill Writing, MCP Implementation
  • Agent Security and Responsible AI
  • Direct experience with LangGraph and LangFuse in production environments
  • Strong technical knowledge, excellent communication skills, and the ability to work effectively within a team are essential for success in this role.

 

Additional Skills:

  • Knowledge of Retail Planning Products
  • DevOps
  • Deploying agent with Performance, Scale, Reliability in Production

 

Our Values

If you want to know the heart of a company, take a look at their values. Ours unite us. They are what drive our success – and the success of our customers. Does your heart beat like ours? Find out here: Core Values

All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability or protected veteran status.

Similar roles