software engineer · qualex consulting services · miami, florida

Hi, I'm Mohith Kanala.

I build the software behind the QLX AI Hub.

At Qualex Consulting Services I help design, code, test and maintain application features for the QLX AI Hub, an enterprise platform where clients run analytics, AI-driven workflows, and marketing and advertising automation in a closed, secure environment. Working with a senior QLX engineer, I build analytics and dashboards, integrations with databases, APIs and AI tools, write the unit and integration tests, and support the deployments.

see the work →
m.sc. thesis · tu delft Coupling a variational multiscale method with a neural network for 3D turbulent channel flow. Physics and machine learning, solving the same equation. read the thesis ↗
7+ years shipping systems · 20K locations at scale · 100M+ records modeled · <5 sec genai response ·
Python · FastAPI · SQL · PostgreSQL · LangGraph · LangChain · OpenAI · Anthropic · Docker · GitHub Actions · AWS · GCP · Azure ·

selected work, 2019 to 2026

Enterprise RAG diagram

01 / enterprise-rag · fortune 500 qsr

Enterprise RAG for a global QSR

Grounded answers, in 20+ languages, in under 5 seconds.

Built the retrieval backbone for customer and vendor AI assistants: semantic search, custom cross-encoder reranking, regional filters, caching, live inventory context, and production guardrails.

Python · Go · AWS Bedrock · Weaviate · Elasticsearch · NeMo Guardrails

~1 TB managed · 5-10 GB daily · NDCG + Recall@K

Forecasting diagram

02 / forecasting · 40+ countries

Demand intelligence at global scale

Forecasts across 15,000-20,000 locations.

Built a near real-time forecasting platform connecting ERP, SCM, POS, ordering, and vendor systems. An XGBoost + LSTM ensemble turned 100M+ historical records into location-level decisions.

XGBoost · LSTM · SageMaker · Kafka · Lambda · SQL

8-12% more accurate · 6-8% fewer stockouts · 100-300 GB daily

Agentic ops diagram

03 / agentic-ops · global cruise line

An ops agent that earns human trust

Autonomous BI operations, with approval built in.

Built an autonomous operations layer spanning 30+ servers and 100+ workflows. It detects anomalies, simulates remediation in a sandbox, and routes structured recommendations for human approval.

Vertex AI · GCP · Power BI · PostgreSQL · Docker · Guardrails AI

60% faster resolution · 40% less manual work · 50-80 signals daily

AI marketing diagram

04 / ai-marketing · closed-loop

Campaigns that optimize themselves

Automation that learns every 6 to 12 hours.

Built an end-to-end Google Ads system combining live performance, trend signals, LLM-generated creative, audience targeting, and an approval-aware optimization loop.

Python · Google Ads API · Vertex AI · Cloud Functions · Docker

15-30% higher CTR · 50-65% less setup · 20+ campaigns