Open to opportunities

Akash Sharma

AI Engineerat Revsure AI

I build production ML systems that convert complex data into reliable business decisions — owned end-to-end, shipped at scale.

4+ years across forecasting pipelines, attribution models, marketing mix modeling, and ML infrastructure.

Akash Sharma

~52%

MAPE Reduction

Booking model error reduced through forecast category feature engineering

~80%

Compute Time Reduction

Modeling pipeline time reduced from 5–6 hours to 1 hour via parallelization

25

Production ML Systems

End-to-end ML systems shipped across 4+ years on a single B2B SaaS platform

~15%

Pipeline Increase

Pipeline grew while cutting channel spend ~50% via marketing mix response curve analysis

Selected Work

Flagship AI Systems

Four flagship AI systems from 25 production ML projects — forecasting, attribution, marketing science, and pipeline intelligence.

Revenue ForecastingApr 2022 – Present

Revenue Forecasting Platform

Production ML system predicting pipeline and booking outcomes at daily frequency across current and future quarters.

~52%

MAPE Reduction

4+

Quarter Horizons

Daily

Scoring Frequency

EOQ ForecastingTime-SeriesLeakage PreventionSHAP Explainability
View Case Study →
Marketing Science2022 – Present

Marketing Mix Modeling Platform

Full-stack marketing attribution and budget optimization platform—from raw channel spend to response curves and scenario planning.

1000+

Feature Scale

0%

Cascade Drift (fixed)

14+

Edge Cases Resolved

Marketing Mix ModelingAdstockHill SaturationResponse Curves
View Case Study →
Marketing Science2022 – 2024

Multi-Touch Attribution System

Probabilistic multi-touch attribution using Markov Chain removal-effect modeling — crediting each channel based on its actual influence on conversion probability across the full customer journey.

Daily

Attribution Scoring

2-Tier

Model Architecture

6

Funnel Stages Covered

Multi-Touch AttributionMarkov ChainMarketing AttributionFirmographic Enrichment
View Case Study →
Pipeline IntelligenceApr 2022 – Dec 2024

Full Pipeline Projection Engine

Central projection system integrating 8+ ML model families into a single daily revenue forecast across four quarter horizons.

8+

ML Model Families

4

Quarter Horizons

Daily

Scoring Frequency

Pipeline ProjectionMicro-Macro ReconciliationRevenue ForecastingDemand Generation
View Case Study →

Core Competencies

What I Bring

Skills built through years of owning production systems end-to-end, not just training models.

Time-Series Forecasting

Expert · 4+ yrs

Marketing Mix Modeling

Expert · 3+ yrs

XGBoost / scikit-learn

Expert · 4+ yrs

Model Explainability (SHAP)

Expert · 3+ yrs

Attribution Modeling

Expert · 4+ yrs

PySpark / BigQuery

Advanced · 2+ yrs

Let's Connect

Let's talk

I'm looking for senior AI engineering and applied ML roles where I can own production systems end-to-end. I respond fastest on LinkedIn.