Senior AI Engineer

As a Senior Data Scientist, you will lead the development of scalable GenAI-powered systems, designing intelligent workflows that leverage large language models (LLMs), vector-based retrieval, and multi-agent orchestration frameworks. You’ll drive solution architecture, mentor junior engineers, and deliver production-ready applications that integrate deeply with business processes and platforms.

Key Responsibilities:

• Lead the design and deployment of GenAI systems leveraging LLMs, retrieval pipelines, and orchestration frameworks for multi-step task execution
• Architect and optimize prompt workflows, including chaining, templating, and context control, for high-accuracy and cost-efficient solutions
• Build and maintain embedding-based retrieval systems using vector databases and context-aware generation techniques (e.g., retrieval-augmented generation)
• Collaborate with product owners and engineering leads to align solution architecture with business objectives
• Guide and mentor junior engineers on best practices in prompt design, token optimization, security controls, and observability patterns
• Define standards for code modularity, response consistency, prompt safety, and testing across LLM-powered applications
• Maintain strong CI/CD practices using version-controlled workflows and cloud-native deployment pipelines
• Evaluate emerging GenAI tooling and provide technical recommendations for experimentation and adoption

Qualifications

• 4+ years of experience in AI/ML solution delivery, with a strong focus on GenAI or LLM-integrated systems
• Expertise in Python (v3.11+) with deep familiarity in LLM APIs, embedding generation, vector-based search, and modular pipeline design
• Proven experience in building and deploying prompt-driven applications at scale
• Solid understanding of agent orchestration patterns, multi-agent task flows, and context layering techniques
• Hands-on experience in cloud-native delivery (preferably Azure), including containerization, CI/CD, and monitoring

Preferred Qualifications

• Exposure to model context protocols (e.g., MCP) and agent-to-agent (A2A) coordination concepts
• Experience with LLM observability tools (latency tracking, relevance scoring, cost management)
• Contributor to internal or open-source projects that showcase applied GenAI, workflow orchestration, or prompt libraries
• Understanding of responsible AI guidelines, token-level safety, and enterprise security standards in GenAI applications