Position Overview

We are seeking innovative and skilled AI Engineers to join our GenAI team. You will play a pivotal role in designing, building, and deploying cutting-edge agentic applications. This role spans from Junior to Senior levels, with expectations adjusted based on experience depth.

Key Responsibilities

• Agentic Application Development: Design and implement autonomous agents and multi-agent systems that can reason, plan, and execute complex tasks.
• Tool & Interface Design: Create robust tools and interfaces that allow agents to interact effectively with external APIs, databases, and software environments.
• System Architecture: Architect scalable and reliable multi-agent systems, ensuring efficient communication and coordination between agents.
• Prompt Engineering: Develop, test, and optimize advanced prompts to guide LLM behavior, ensuring high accuracy and reliability in agent outputs.
• Cloud Deployment: Deploy, monitor, and maintain AI and agentic applications on cloud platforms (Azure/AWS), focusing on scalability, latency, and cost-optimization.
• Collaboration: Work closely with cross-functional teams to integrate agentic solutions into broader product ecosystems.
• Innovation: Stay at the forefront of Generative AI research, experimenting with new frameworks and techniques to drive continuous improvement.

Knowledge and Attributes

Core Technical Skills

• Programming: Proficiency in Python is essential. Experience with asynchronous programming and API development (FastAPI/Flask).
• Generative AI & LLMs: Deep understanding of Large Language Models (LLMs), their capabilities, limitations, and tuning techniques (RAG, fine-tuning).
• Agent Frameworks: Hands-on experience with modern agent frameworks such as:
  • Google GenAI SDK / Vertex AI Agent Builder
  • Anthropic Claude SDK / Tools / Skills
  • Microsoft Agent Framework
  • LangChain / LangGraph
• Agent Design: Solid grasp of agent design patterns (ReAct, Chain-of-Thought, planning, reflection) and tool-use definitions.

Cloud & DevOps

• Cloud Platforms: Strong experience with Azure / AWS / GCP ecosystems.
• Deployment: Expertise in deploying AI applications using containerization (Docker, Kubernetes) and serverless technologies (Azure Functions, AWS Lambda, GCP Cloud Run).
• MLOps/LLMOps: Familiarity with pipelines for evaluating, monitoring, and managing the lifecycle of LLM-based applications.

Experience Levels

Mid-Level Engineer

• Experience: 3-5 years in software/AI engineering with proven experience building LLM applications.
• Focus: Designing agent workflows, optimizing prompt performance, managing cloud infrastructure for AI apps, and mentoring junior members.

Senior Engineer

• Experience: 5+ years in AI/Software Engineering with significant expertise in Generative AI and system architecture.
• Focus: Leading the architecture of complex multi-agent systems, defining best practices for agent design, driving strategic technical decisions, and overseeing large-scale deployments.

Soft Skills

• Excellent problem-solving and analytical skills.
• Strong communication skills to articulate complex technical concepts to stakeholders.
• Ability to work effectively in a fast-paced, collaborative global environment.