Job Description

Key Responsibilities

• Design, develop, and deploy production-ready Generative AI capabilities, including LLM-based applications and RAG pipelines.
• Implement and optimize LLM workflows, covering prompt engineering, context management, retrieval strategies, and model evaluation.
• Build scalable backend services to support GenAI applications, ensuring reliability, performance, and maintainability.
• Integrate GenAI tooling, such as orchestration frameworks, vector databases, and embedding pipelines, into end-to-end solutions.
• Conduct assessment and optimization of GenAI systems, including latency, cost, quality, and reliability improvements.
• Rapidly prototype new GenAI features while maintaining clean architecture, testability, and long-term maintainability.
• Collaborate with platform, product, and data teams to translate business requirements into robust AI-powered solutions.
• Contribute to best practices, documentation, and design reviews for AI engineering and backend development.

Required Qualifications

• 5+ years of overall software engineering experience, with a minimum of 2+ years hands-on experience in AI/ML or Generative AI.
• Demonstrated experience delivering actual production implementations of AI or GenAI systems (not just research or prototypes).
• Strong understanding and practical experience with:

• Generative AI tools and frameworks (e.g., LLM orchestration, vector databases, prompt/context engineering).
• RAG architectures, embeddings, and retrieval strategies.
• Solid foundation in software engineering principles, including:

• Object-Oriented Programming (OOP)
• SOLID principles
• 12-factor application design
• Proficiency in building cloud-native applications, including containerization, CI/CD, and scalable service deployment.
• Strong programming skills and ability to write clean, maintainable, and testable code.

Preferred Qualifications

• Experience operating GenAI workloads in production, including monitoring, logging, and cost optimization.
• Familiarity with multiple LLM providers and model deployment strategies.
• Exposure to MLOps or LLMOps practices.
• Experience working in agile or fast-paced product development environments.

Skills Required