I build the systems that make ambition executable.

I began in the automotive space, designing and delivering 20+ RPA bots for a global brand. The work connected systems that were never designed to work together—Citrix, Mainframe, Oracle EBS, Microsoft Dynamics, email, and complex desktop workflows.

At R Systems, I led a greenfield automation program for a major Japanese automotive organisation. I was deployed onsite as Lead Engineer and took ownership from process discovery and architecture through production environment setup and delivery.

The flagship import-export automation dealt with genuine operational complexity: government notifications, customs, tax, INCOTERMS, invoices, Free Trade Agreements, and highly variable source documents. It converted a difficult, exception-heavy process into a dependable operating flow.

I also automated procurement and invoicing—from consolidating RFQs and identifying anomalies to plant assignment, vendor reconciliation, Oracle EBS uploads, IRN generation, and indexing. The outcome was not simply faster processing; it was a more visible, consistent, and scalable operation.

At Zensar, I worked with a leading U.S. modem and communications-device manufacturer to automate core finance operations. The mandate covered accounts payable, accounts receivable, debit notes, and chargebacks—processes where accuracy and auditability are as important as speed.

I delivered four end-to-end automations across email, Oracle EBS, Salesforce, and internal business applications. Each solution was designed around the full process rather than an isolated task, so the work could survive hand-offs, exceptions, and real operational change.

The automations scaled to more than 100 vendors, eight geographies, and eight languages. That breadth demanded robust design: clear exception paths, reliable data handling, and an operating model that could be used consistently by distributed teams.

Earlier and later work deepened that finance lens through reconciliations spanning Excel, SAP, APIs, and databases, plus automated invoice generation and vendor matching. These projects helped turn finance from a queue of manual checks into a system with a clearer source of truth.

With a Fortune 500 EdTech partner, we moved beyond single-purpose AI features to build a coordinated set of learning agents. The work began when generative AI was still early, which meant product judgment and system design mattered as much as model capability.

Using AutoSage v2 and its API layer, we created agents for generating learning material—up to 100 pages at a time—question papers, presentations, and exam evaluation. The work used early multi-agent patterns to make complex content workflows more deliberate and repeatable.

The platform also supported faculty invoicing and field-sales training, extending the value from classroom content into the operating machinery around education. This made the product useful to more of the organisation, not only to individual educators.

I am also a co-inventor on four jointly filed patents in the EdTech space. That experience reinforced a principle I bring to every AI product: the goal is not impressive generation in isolation, but reliable value inside a real workflow.

For a Berlin-based venture capital fund, I led the development of AgentOS: an interoperating autonomous system designed to support the full lifecycle of a company. It brought company formation, HR, finance, sales, and marketing into one agentic operating layer.

The engagement also included a company-brain initiative, giving teams a more useful way to access and act on organisational knowledge. Instead of treating information retrieval as the endpoint, the system was conceived around context, coordination, and action.

We also built startup screening and scoring capabilities based on a proprietary evaluation mechanism, alongside CRM and AI-powered outreach. The result was a set of tools that could improve the speed and consistency of early-stage decision-making without reducing it to a black box.

Alongside this work, I have helped early products find their footing—from a legal-data chatbot for state and county websites to an AI-powered property-management centralisation app and an intelligence layer for an AdTech partner. These projects taught me to balance speed, product clarity, and technical durability.

Some of the most consequential AI work lives where communication, care, and compliance intersect. I have led product work on a voice-AI platform for outbound calling, designed to make high-volume outreach more timely, consistent, and operationally usable.

In the HR benefits space, I helped shape a joint venture powered by AutoSage v4. The focus was on bringing intelligence into a workflow where decisions affect real employee experiences—requiring an approach that values reliability and thoughtful system design.

I have also worked on a revenue-cycle management product focused on eligibility and denial management. Here the challenge is not merely extracting data; it is coordinating evidence, workflow, and action so teams can resolve issues with less friction.

Across these sensitive domains, the standard is higher. I bring an enterprise mindset to architecture, cost management, and compliance—including SOC 2 and HIPAA considerations—so that useful AI can also be trusted in production.