Software foundations.
AI systems.
Product thinking.

From software engineering to AI systems.

I started my career building software from the ground up — working across frontend, backend, APIs, messaging systems, data pipelines, cloud infrastructure, and production operations.

Over five years, that foundation grew into system design, product ownership, technical leadership, and increasingly complex AI-powered products.

Today, I work primarily on AI Engineering: building systems around LLMs, RAG, agents, MCP, conversational AI, evaluation, reliability, and production deployment.

The direction has changed, but the foundation remains the same: strong engineering, clear systems thinking, and building for real users.

Five years of building real systems.

My software engineering career began with customer-facing messaging and SaaS platforms, where reliability, production constraints, and real business requirements mattered every day.

I progressed from intern to software engineer and then senior engineer, working across customer engagement, CRM, messaging, analytics, and conversational systems.

I built event-driven workflows, APIs, backend services, analytics pipelines, and cloud infrastructure while working with systems serving thousands of businesses.

That experience gave me something I carry into AI engineering today: AI systems still need to behave like production software.

Engineering beyond the code.

As my engineering experience grew, I moved closer to product decisions, system architecture, and cross-functional leadership.

At MarketBuzz, I worked across engineering and product — translating business problems into technical direction, leading architecture and product workshops, aligning teams around execution, and mentoring engineers.

I learned to think beyond whether something can be built and ask a broader set of questions:

• Should we build it?
• What problem does it solve?
• How should the system evolve?
• What does it take to operate it in production?

Now building AI-native systems.

My current focus is AI Engineering — not simply adding an LLM to an existing application, but designing the systems around intelligent behavior.

I work across retrieval, context construction, agent orchestration, tool calling, memory, human-in-the-loop workflows, evaluation, observability, reliability, and deployment.

Recent work spans agentic research systems, MCP infrastructure, multi-agent product workflows, conversational AI, multimodal retrieval, and AI-powered automation.

Technology is only useful when it works for people.

I care about the engineering underneath a product, but also about the people using it, the business behind it, and the context in which it operates.

I believe good systems need more than technical sophistication. They need clear purpose, thoughtful design, reliable behavior, and an understanding of the people they serve.

That’s why my approach sits across tech, business, and human — building systems that are technically sound, useful in practice, and designed with intention.

Frequently Asked Questions