Job Summary

The Agentic AI Engineer II supports the development, integration, and improvement of agentic AI components and workflows within defined solution areas. The role implements approved designs as reliable agents, orchestration flows, APIs, and integrations using large language models, enterprise data, and external tools. Working under the guidance of architects and senior engineers, and collaborating with data engineers and product teams, the engineer follows established patterns for testing, deployment, monitoring, security, and Responsible AI. The role primarily focuses on hands-on implementation, troubleshooting, documentation, and contribution to reusable delivery assets.

Key Responsibilities

• Develop, configure, and test agentic AI components using large language models and approved enterprise platforms.
• Implement prompt flows, retrieval, agent orchestration, tool use, memory, and model interaction patterns based on provided designs.
• Develop and maintain APIs, pipelines, and integrations that connect agentic AI capabilities with products and business workflows.
• Work with data engineers to connect suitable datasets and knowledge sources for grounding and evaluation.
• Follow established Responsible AI, security, privacy, explainability, and data-governance controls.
• Perform functional testing and basic monitoring of model and agent performance; troubleshoot defects and implement agreed improvements.
• Support CI/CD activities, operational documentation, reusable components, and production-support tasks.
• Build familiarity with relevant agentic frameworks, LLM APIs, and open-source tools, and share implementation learnings with the team.

Skill Requirements

Must Have Skills:

• Proficiency in Python.
• Experience designing and consuming REST APIs.
• Hands-on experience with LLM APIs such as OpenAI, Gemini, or Anthropic.
• Experience with LangChain or LangGraph.
• Practical knowledge of prompt engineering.
• Foundational understanding of vector database concepts.
• Working knowledge of Git and CI/CD fundamentals.
• Foundational understanding of NLP, LLM concepts, and data pipelines.
• Good debugging, analytical, and problem-solving skills.

Good to Have Skills:

• Exposure to CrewAI, Google Agent Development Kit (ADK), Model Context Protocol (MCP), Agent2Agent (A2A), or similar technologies.
• Experience with Vertex AI or comparable cloud AI platforms.
• Exposure to PyTorch or TensorFlow.
• Understanding of model fine-tuning concepts.
• Experience with SQL, machine learning, big data, or additional database technologies.
• Exposure to Azure, AWS, or GCP and MLOps tools for model deployment.

Other Requirements

• Education: bachelor’s or master’s degree in computer science, Artificial Intelligence, Data Science, Machine Learning or a related field.

• Experience: 2–5 years of hands-on experience in software engineering, with at least 1 year of exposure to generative AI or LLM-based applications.
• Adept at critical thinking and logical reasoning for problem-solving Be good at teamwork and delivering under pressure
• Experience with LLMs Understanding of good design principles and patterns
• Solid appreciation of AI/ML concepts Extremely dynamic and enthusiastic about technology Development experience with one or more of these technologies: C++, Java, JavaScript, HTML, C#, Python, node.js Be able to adapt quickly to new challenges and an evolving technology stack
• Excellent written and verbal communication skills.
•  Fluent English is essential Strong analytical and problem-solving skills.
• Demonstrating a customer-focused attitude;
•  Excellent communication skills (listening, presenting, writing, formal and informal)
• Self-motivated, self-driven, curious, open-minded, resourceful, and flexible with the ability to learn quickly.

Strong communication and interpersonal skills for effective collaboration with team members and stakeholders