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

Overview

Design, build, and maintain production-grade agent solutions as a hands-on Agent Engineer using Python, OpenAI Agents SDK, LangGraph, and LangFuse. Deliver features for multi-tenant services and support testing, CI/CD, security, observability, incident response, and operational excellence.

What you'll do

• 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; participate in mutation testing cycles and remediate identified gaps with guidance from senior engineers.
• Collaborate in Agile ceremonies, including backlog grooming, sprint planning, daily standups, and retrospectives.
• 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 by providing technical analysis, implementing remediation tasks, and documenting lessons learned.
• Incorporate information-security and data-privacy best practices in design, implementation, and code reviews.
• Monitor and improve observability by adding meaningful metrics, logs, and traces.
• Keep up to date with agent development patterns, testing techniques, and observability tooling and propose practical improvements.
• Provide constructive code review feedback and incorporate reviewer suggestions.
• Produce and maintain onboarding documentation, runbooks, and troubleshooting guides.
• Identify and implement small refactors and focused performance improvements, and escalate larger refactor or architectural changes for team prioritization.
• 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 work aligns with the team vision and communicate impediments that could block delivery.

What you'll need

• BE/B.Tech, ME/M.Tech, or MCA.
• 5 to 8 years of experience.
• Proficiency with Python.
• Proficiency with OpenAI Agents SDK.
• Proficiency with RAG.
• Proficiency with Prompt Engineering.
• Proficiency with Context Engineering.
• Experience in benchmarking Evaluation sets and writing evaluators.
• Knowledge of Multi Agent Orchestration, including Worker (Supervisor) and Concurrent (Fan-Out/Fan-In).
• Skill Writing.
• MCP Implementation.
• Agent Security and Responsible AI.
• Direct experience with LangGraph and LangFuse in production environments.
• Strong technical knowledge.
• Excellent communication skills.
• Ability to work effectively within a team.

Nice to have

• Knowledge of Retail Planning Products.
• DevOps experience deploying agents with Performance, Scale, and Reliability in Production.

Details

• Location: Hyderabad.