Raj Gunda

Building SpaceOS, a downstream spacetech platform converting Earth Observation data into predictive economic intelligence for SMB expansion. We transform multispectral, thermal, and night-time luminosity data into revenue forecasting and location viability signals using geospatial preprocessing, proprietary feature engineering, and spatio-temporal ML models. Focus Areas: • Satellite-to-signal intelligence architecture • Geospatial data pipelines (cloud masking, NDVI, LST, luminosity growth) • Demand prediction & expansion scoring models • AI-driven economic signal extraction • Scalable SaaS delivery for space-enabled intelligence Leading product direction, system architecture, and deeptech execution at the intersection of AI, geospatial systems, and commercial spacetech applications.

AI Enabled SAAS.

Worked on large-scale data-driven systems at a telecom enterprise, collaborating closely with engineering, analytics, and product teams. This role shaped my approach to systems thinking, experimentation, and reliability, which now directly informs my work on AI-powered agent systems and backend orchestration. What I focused on: • Designing measurement and attribution systems with engineers • Translating business goals into technical tracking and data requirements • Running structured experimentation (A/B tests) at scale • Improving system reliability across funnels, events, and analytics • Working cross-functionally with product and engineering stakeholders What this led to: A strong foundation in how complex systems behave in production, which I now apply to: • LLM-powered agent workflows • Tooling, orchestration, and reliability • Building AI systems meant for real usage, not demos

Worked on event-driven data systems within a large-scale enterprise environment, supporting backend analytics infrastructure and internal data consumers. Technical responsibilities: • Designed and maintained event schemas for user-interaction tracking • Implemented client-side and server-side instrumentation • Integrated events into data ingestion pipelines (ETL/ELT) • Validated data consistency, idempotency, and completeness across pipelines • Assisted in maintaining analytics data stores and reporting layers • Supported A/B experimentation frameworks (experiment assignment, metric collection, result validation) • Investigated data anomalies using logs, metrics, and dashboards • Documented system contracts, dependencies, and failure modes Technical focus: • Event-driven architectures • Data pipelines & ingestion systems • Schema design & validation • Observability (logs, metrics, dashboards) • Experimentation infrastructure • Cross-service data integration • Production data reliability Outcome: Built a strong foundation in backend data systems, instrumentation, and system reliability, directly applicable to later work on distributed backend platforms and AI agent orchestration systems.

➡ Specialized in Marketing strategy, digital transformation, and business analytics. ➡ Focused on applying data-driven decision-making to SaaS and technology business models. ➡ Worked on projects bridging technology and customer experience.

Studied core Computer Science and Information Technology subjects including software engineering, databases, and cloud computing. ➡ Active in coding projects and technical fests, with early exposure to building scalable applications. ➡ Laid the foundation for later work in Salesforce and SaaS product development.