Senior GenAI Engineer

We are seeking a Senior GenAI Engineer to lead the development and optimization of AI-powered applications.

This role involves implementing cutting-edge solutions that integrate large language models (LLMs) and ensuring scalable, reliable, and efficient deployment in cloud-based environments.

Responsibilities

• Develop and optimize backend services for scalable AI/LLM applications
• Integrate and manage LLM-based applications in cloud environments, with a preference for Azure
• Implement CI/CD pipelines to automate deployment processes
• Monitor and improve the performance, cost-efficiency, and reliability of AI services
• Ensure observability and logging for performance tracking of LLM APIs
• Collaborate with AI/DS and DevOps teams to improve workflows and establish system reliability
• Build APIs and microservices to support AI-powered features
• Solve challenges related to latency, cost control, retries, and fallbacks in LLM-backed applications
• Utilize SQL/NoSQL databases, Redis, and Kafka for backend architecture
• Leverage tools like Databricks and Model Context Protocol to enhance AI workflows

Requirements

• Minimum 3 years of experience in Python backend engineering with expertise in FastAPI
• Proficiency in developing and managing GenAI applications with a focus on large language models (LLMs)
• Knowledge of prompt engineering, agentic workflows, and orchestration patterns
• Familiarity with LLM API integration and operational best practices
• Competency in scalable backend architecture for LLM-powered APIs
• Working knowledge of SQL/NoSQL databases, Redis, and Kafka
• Experience working with Databricks and MCP (Model Context Protocol)
• Excellent English communication skills at a B2+ level

Nice to have

• Expertise in agentic workflows
• Familiarity with Databricks and Model Context Protocol