Software Engineer I – AI Agent Developer at Zebra

Are you passionate about cutting-edge AI technologies and autonomous agent development? The Software Engineer I – AI Agent Developer position at Zebra Bangalore offers an exceptional opportunity for early-career professionals (0-2 years experience) to work on developing autonomous AI agents, multi-agent orchestration, and RAG systems in a hybrid work environment.

Zebra Technologies is a global leader in enterprise technology solutions, creating innovative ways of working for organizations worldwide. This role focuses on developing AI agents capable of reasoning, orchestrating workflows, and executing tasks across systems while bridging LLM outputs with backend logic and APIs for self-operating workflows. You’ll work with cutting-edge frameworks like LangGraph, LangChain, and implement Retrieval-Augmented Generation systems.

🚀 About the AI Agent Developer Role at Zebra

This position centers on building autonomous AI agents that can reason, make decisions, and orchestrate complex workflows across enterprise systems. You’ll develop multi-agent pipelines, implement RAG systems for enhanced AI applications, and create communication interfaces between AI agents and backend services. The role combines AI/ML expertise with strong backend engineering skills to build production-grade agentic AI systems.

📊 Job Details

About Zebra Technologies

Company Overview

Zebra Technologies is a global innovator in enterprise solutions:

• Community of Innovators: Collaborative culture creating new ways of working
• Global Presence: Serving organizations worldwide with smart solutions
• Culture: United by curiosity and a culture of caring
• Mission: Anticipate customer and partner needs, solve their challenges
• Values: Employees are seen, heard, valued, and respected

Primary Job Responsibilities

Multi-Agent Orchestration Pipeline Development

• Develop sophisticated multi-agent orchestration pipelines using frameworks like LangGraph or Haystack
• Design agent communication protocols and coordination mechanisms
• Implement task delegation and workflow distribution across multiple AI agents
• Create agent supervisors for managing complex multi-agent systems
• Build fault-tolerant orchestration with agent monitoring and recovery
• Optimize agent collaboration patterns for efficiency and reliability
• Implement agent memory systems for context preservation across interactions

Data Pipelines and Workflow Orchestration

• Develop and manage robust data pipelines for AI and ML model operations
• Create orchestration workflows integrating multiple AI/ML models
• Implement ETL processes for AI training and inference data
• Build scalable data processing pipelines handling large-scale data
• Design workflow automation for model deployment and monitoring
• Integrate data quality checks and validation mechanisms
• Optimize pipeline performance for real-time and batch processing

Retrieval-Augmented Generation (RAG) Implementation

• Implement and optimize Retrieval-Augmented Generation systems for AI applications
• Build vector databases and embedding systems for efficient retrieval
• Design chunk strategies and indexing mechanisms for optimal retrieval
• Implement hybrid search combining semantic and keyword-based retrieval
• Optimize RAG pipelines for latency and accuracy
• Create re-ranking mechanisms for improved retrieval quality
• Integrate RAG systems with LLMs for enhanced context-aware responses

Agent Communication and API Integration

• Build agent communication interfaces enabling inter-agent coordination
• Develop API integration layers connecting AI agents with backend systems
• Create REST and gRPC interfaces for agent-to-system communication
• Implement event-driven architectures for asynchronous agent operations
• Design protocol buffers and message schemas for efficient communication
• Build API gateways and service meshes for agent infrastructure
• Ensure security and authentication in agent-to-service communications

Context Management and Tool-Use Implementation

• Implement sophisticated context management for maintaining agent state
• Build tool-use capabilities enabling agents to interact with external systems
• Create function calling interfaces for agents to execute specific actions
• Develop context windowing strategies for managing long conversations
• Implement memory systems (short-term, long-term, episodic)
• Design context compression techniques for efficient token usage
• Build error detection and recovery mechanisms for robust agent operation

Cross-Functional Collaboration

• Collaborate with Prompt Engineers to ensure reasoning consistency
• Work with Model Engineers on model fine-tuning and optimization
• Partner with backend teams for system integration
• Coordinate with product teams on agent behavior and capabilities
• Share knowledge and best practices across engineering teams
• Participate in code reviews and architectural discussions
• Contribute to technical documentation and knowledge base

• Indicus Software Hiring Technical Intern AI

Help a friend land their next role. Share now!

📋 Required Qualifications and Skills

Educational Requirements

Required: Bachelor’s Degree

Preferred Fields:

• Computer Science
• Software Engineering
• Artificial Intelligence
• Data Science
• Information Technology
• Related quantitative disciplines

Experience Requirements

Required: 0 to 2 years of professional experience

Acceptable Experience Types:

• Full-time software development positions
• AI/ML internships or research projects
• Academic projects in AI agents or LLMs
• Open-source contributions to AI frameworks
• Personal projects in agentic AI or RAG systems

Required Technical Skills

• Meltwater Hiring AI Engineer

AI/ML Specific Skills

• Understanding of Large Language Models (LLMs) and their capabilities
• Knowledge of prompt engineering and LLM optimization
• Experience with vector databases (Pinecone, Weaviate, Chroma)
• Familiarity with embedding models and semantic search
• Understanding of RAG architecture and components
• Knowledge of agent frameworks (LangGraph, Haystack, AutoGPT)

Nice-to-Have Skills

• Experience with specific agent frameworks:
  • LangGraph for complex agent workflows
  • Haystack for RAG pipelines
  • CrewAI or AutoGen for multi-agent systems
• Knowledge of OpenAI, Anthropic, or other LLM APIs
• Experience with containerization (Docker, Kubernetes)
• Understanding of distributed systems and message queues
• Familiarity with cloud platforms (AWS, Azure, GCP)
• Knowledge of MLOps practices and tools
• Experience with monitoring and observability tools
• Understanding of security best practices for AI systems

Follow us on LinkedIn for the latest updates

Follow us on Threads for the latest updates

Subscribe ▶️ YouTube Channel for Latest Updates

💰 Expected Salary Range

Note: Zebra Technologies offers competitive compensation packages for AI/ML roles.

• Data Scientist at IBM

Application Tips

• Highlight AI agent or LLM projects with concrete technical details
• Showcase RAG implementations with retrieval metrics and evaluations
• Emphasize experience with LangChain, LangGraph, or similar frameworks
• Include projects demonstrating multi-agent coordination
• Demonstrate strong Python skills with async and API development
• Express genuine passion for autonomous AI and agentic systems
• Prepare to discuss trade-offs in agent design and orchestration
• Research Zebra’s enterprise solutions and potential AI applications
• Show understanding of RAG architecture and optimization techniques
• Include GitHub profile with well-documented AI projects
• Mention any contributions to AI framework open-source projects
• Prepare questions about Zebra’s AI strategy and team structure

Disclaimer: This job information is collected from official and publicly available sources. We do not charge any fees for job applications, do not guarantee recruitment, and are not responsible for any loss or damage arising from reliance on this information.