About this role
• Architect enterprise-grade GenAI systems using modular LLM APIs, agent orchestration frameworks, and embedding pipelines • Design and implement autonomous agent workflows with context management, multi-agent coordination, and task delegation • Optimize performance, latency, and accuracy through experimentation with prompt strategies, retrieval layers, and caching logic • Lead solution reviews, enforce prompt safety and governance, and ensure alignment with security protocols • Collaborate with platform, product, and engineering leads to define reusable patterns and scalable AI capabilities • Guide engineering pods on GenAI design principles, system reliability, and prompt lifecycle management • Build and maintain reusability assets — SDKs, templates, shared agent logic — to accelerate delivery velocity across teams • Stay up to date with advancements in LLM tooling, orchestration abstractions, and prompt optimization techniques
Required Qualifications: • 6–8+ years of experience in AI/ML engineering, with a strong focus on designing and scaling GenAI applications • Deep proficiency in Python 3.11+ and experience with LLM APIs, vector databases, embedding generation, and agent coordination • Hands-on expertise in architecting agent-based workflows using framework-agnostic orchestration patterns • Proven track record in deploying secure, cost-effective, cloud-native GenAI solutions (preferably in Azure ecosystem) • Solid grasp of CI/CD, containerization, and model monitoring practices
Preferred Qualifications: • Exposure to model context protocols (MCP) and autonomous agent-to-agent (A2A) interactions • Contributor to reusable GenAI accelerators, prompt chaining templates, or internal developer tools • Familiarity with governance and observability tools for LLM workflows (e.g., cost tracking, safety controls, token usage analytics) • Ability to simplify and communicate technical decisions to both engineers and non-technical stakeholders