- Architect Agentic Systems: Design and implement production-grade agentic workflows—including Reflection, Self-Correction, Planning, and Multi-Agent Orchestration patterns—to power a growing portfolio of AI-driven product capabilities.
- Operationalize Agents in Production: Own the full lifecycle from rapid prototype to production deployment. Build agent systems with real-world constraints in mind: token budgets, latency targets, graceful degradation, and cost observability.
- Evolve Multi-Model Intelligence: Develop systems that synthesize outputs from ChatGPT, Gemini, and Perplexity to identify sentiment discrepancies, detect brand hallucinations, and surface actionable intelligence for customers.
- Build Scalable Cloud Infrastructure: Design and maintain serverless backend services using Python and AWS Lambda, ensuring agents perform efficiently at scale with proper observability.
- Drive Evaluation and Quality: Build LLM-as-a-Judge evaluation frameworks, trace-based testing pipelines, and quality feedback loops that keep agent output reliable as models and prompts evolve.
- Collaborate Across Teams: Work closely with Software Engineers and Product Managers to integrate agentic behaviors into production frameworks, ensuring AI systems are stateful, observable, and resilient.
PythonC#.NET+2 more