Founding Machine Learning Engineer (Ads & Signal Engineering)

Qualifications

• 5+ years Data Science experience with direct AdTech/MarTech overlap, including hands‑on work with: analytics tagging, website analytics, server‑side integrations, CAPI / Conversions API and technical marketing data flows
• Proven 0 to 1 product builder with a strong ownership mindset, have built systems/models/data products from scratch
• Strong ML foundations + applied instincts, able to reason from business objective > data limitations > modeling approach > deployment path
• Hands‑on production ML experience, including: training pipelines, deployment to production and monitoring + observability
• Experience with LTV modeling, including: probabilistic/BTYD‑style thinking, survival/retention modeling, regression/classification for value prediction and calibration + drift handling
• Excellent Python + SQL, comfortable working in modern data stacks and cloud environments
• Tech Stack
• Core: Python, SQL, Docker

Benefits

• Compensation & Benefits
• Base Salary: $70,000 – $100,000 (experience‑dependent)
• Equity: Meaningful early‑stage equity; major portion of compensation delivered in ownership
• Growth Path: Strong candidates may grow into Co‑Founder or CTO–level responsibility based on performance, ownership, and contribution
• Remote Flexibility: Fully remote role; NYC or SF preferred

Responsibilities

• If you’ve built production-grade LTV/propensity models, love messy real-world data, and get excited about adtech mechanics (CAPI, conversion quality, identity, attribution constraints), you’ll feel at home here
• You’ll design and ship user-level pLTV systems and the signal pipeline that turns events + transactions into deployable features with near-real-time scoring
• You’ll own activation-ready outputs (value tiers/deciles, conversion value mappings, high‑value audience definitions, bidding signals), plus the orchestration layer that moves data warehouse → models → ad platforms reliably and safely
• High ownership, fast iteration, real customer impact
• Design & ship LTV/pLTV systems end-to-end: data ingestion → feature engineering → model training → evaluation → deployment → monitoring
• Build models for adtech realities: handle delayed conversions, sparse signals, attribution changes; ensure calibration, drift detection, and retraining cadence
• Own the signal pipeline: convert raw events/transactions into activation-ready features for near‑real‑time scoring; define value tiers/deciles, conversion value mappings, high‑value audiences, and bidding signals
• Orchestrate activation flows: reliably move data warehouse → models → ad platforms (Meta CAPI, Google Enhanced/Offline Conversions) within platform constraints
• Implement MLOps: reproducible training, CI/CD for models, logging, data‑quality checks, drift/performance alerting, and production observability
• Translate business outcomes into model objectives: profit, payback, repeat rate → measurable objectives and activation strategies; partner with Product/GTM
• Codify the Signal Engineering playbook: modeling standards, calibration guidelines, drift handling, retraining cadence
• Optimize performance: streamline pipelines, near‑real‑time scoring paths, and integrations; iterate quickly based on real customer feedback
• Data/Warehouse: BigQuery (+ dbt‑style transforms), event + transactional pipelines (Shopify/CRM/GA4/CDPs)
• Cloud: GCP (Cloud Run, Pub/Sub/queues, scheduled jobs), secure APIs + services
• ML: scikit‑learn + (XGBoost/LightGBM/CatBoost) + optional PyTorch; MLflow/W&B‑style tracking
• Orchestration: Airflow/Prefect/Dagster‑style patterns (approach over logo)

Full Description

Founding ML Engineer (Ads & Signal Engineering)

Location: open to New York or San Francisco

Role Type: Full-Time

Start Date: March 16

Company: AdZeta — https://www.adzeta.io

Company Overview

AdZeta is building the signal engineering + activation layer for modern growth teams.

We unify first‑party data, predict customer LTV, and push value signals into Google/Meta (and beyond) so brands can bid for profit, not just ROAS.

If you’ve built production-grade LTV/propensity models, love messy real-world data, and get excited about adtech mechanics (CAPI, conversion quality, identity, attribution constraints), you’ll feel at home here.

Role Description

You’ll design and ship user-level pLTV systems and the signal pipeline that turns events + transactions into deployable features with near-real-time scoring.

You’ll own activation-ready outputs (value tiers/deciles, conversion value mappings, high‑value audience definitions, bidding signals), plus the orchestration layer that moves data warehouse → models → ad platforms reliably and safely. High ownership, fast iteration, real customer impact.

Responsibilities

• Design & ship LTV/pLTV systems end-to-end: data ingestion → feature engineering → model training → evaluation → deployment → monitoring.

• Build models for adtech realities: handle delayed conversions, sparse signals, attribution changes; ensure calibration, drift detection, and retraining cadence.

• Own the signal pipeline: convert raw events/transactions into activation-ready features for near‑real‑time scoring; define value tiers/deciles, conversion value mappings, high‑value audiences, and bidding signals.

• Orchestrate activation flows: reliably move data warehouse → models → ad platforms (Meta CAPI, Google Enhanced/Offline Conversions) within platform constraints.

• Implement MLOps: reproducible training, CI/CD for models, logging, data‑quality checks, drift/performance alerting, and production observability.

• Translate business outcomes into model objectives: profit, payback, repeat rate → measurable objectives and activation strategies; partner with Product/GTM.

• Codify the Signal Engineering playbook: modeling standards, calibration guidelines, drift handling, retraining cadence.

• Optimize performance: streamline pipelines, near‑real‑time scoring paths, and integrations; iterate quickly based on real customer feedback.

Basic Qualifications

• 5+ years Data Science experience with direct AdTech/MarTech overlap, including hands‑on work with: analytics tagging, website analytics, server‑side integrations, CAPI / Conversions API and technical marketing data flows

• Proven 0 to 1 product builder with a strong ownership mindset, have built systems/models/data products from scratch

• Strong ML foundations + applied instincts, able to reason from business objective > data limitations > modeling approach > deployment path

• Hands‑on production ML experience, including: training pipelines, deployment to production and monitoring + observability

• Experience with LTV modeling, including: probabilistic/BTYD‑style thinking, survival/retention modeling, regression/classification for value prediction and calibration + drift handling

• Excellent Python + SQL, comfortable working in modern data stacks and cloud environments

Preferred Qualifications

• Advanced AdTech/MarTech experience, including:Meta CAPI, Google Ads Enhanced Conversions / Offline Conversions, audience/CRM activation and conversion quality + incrementality intuition

• Identity / data joining experience, such as: hashed PII, multi‑key matching, deduping and event stitching

• Experience with streaming / near‑real‑time systems and event pipelines

• Familiarity with experimentation + measurement frameworks, including: uplift / incrementality testing, MMM and attribution‑constraint environments

Tech Stack

• Core: Python, SQL, Docker

• Data/Warehouse: BigQuery (+ dbt‑style transforms), event + transactional pipelines (Shopify/CRM/GA4/CDPs)

• Cloud: GCP (Cloud Run, Pub/Sub/queues, scheduled jobs), secure APIs + services

• ML: scikit‑learn + (XGBoost/LightGBM/CatBoost) + optional PyTorch; MLflow/W&B‑style tracking

• Orchestration: Airflow/Prefect/Dagster‑style patterns (approach over logo)

• Adtech: Meta CAPI, Google Ads integrations (value signals, offline events, audience sync)

Compensation & Benefits

• Base Salary: $70,000 – $100,000 (experience‑dependent)

• Equity: Meaningful early‑stage equity; major portion of compensation delivered in ownership

• Growth Path: Strong candidates may grow into Co‑Founder or CTO–level responsibility based on performance, ownership, and contribution

• Remote Flexibility: Fully remote role; NYC or SF preferred

Additional Job Application Terms

This job is part of LinkedIn’s Full-Service Hiring beta program.

Eligibility is limited to candidates located in and performing services in the United States, excluding those based in Alaska, Hawaii, Nevada, South Carolina, or West Virginia.

We’re committed to making our hiring process as smooth and timely as possible, and we understand that waiting to hear back can add to the anticipation.

If you’re a potential fit, our team will reach out within two weeks to progress you to the next stage. If you don’t hear from us in that time, we encourage you to explore other opportunities with our team in the future, and we wish you the very best in your job search.