ML Engineer — Deal Intelligence & Scoring Platform
LiveWire Picks is building a ladies-focused fashion and beauty deal discovery platform that helps shoppers find products worth buying, not just products with fake markdowns, expired offers, or inflated discounts.
Our goal is to make online deal hunting smarter, cleaner, and more trustworthy. We scan retail and marketplace deals, evaluate them using Livewire signals, and present users with clear explanations such as why a deal stands out, what to watch for, and whether it is truly worth attention.
We are looking for an experienced ML Engineer to help build the intelligence layer behind LiveWire Picks.
- Company
- LiveWire Picks
- Location
- Remote
- Openings
- 1
- Type
- Full-time / Contract-to-hire possible
- Experience
- 5-6+ years preferred
Role Overview
As an ML Engineer, you will help design and build the scoring, ranking, classification, and recommendation systems that power our deal discovery engine. You will work on models and pipelines that evaluate products using signals such as price history, coupon mechanics, review trustworthiness, product usefulness, merchant quality, category fit, and user behavior. This is a hands-on role for someone who can move between machine learning, backend logic, data pipelines, LLM integration, experimentation, and product-focused AI.
Best fit
This role is for someone who wants to help make deal discovery more useful, more trusted, and easier for everyday shoppers to understand.
Responsibilities
- Design and improve LiveWire Picks' Livewire scoring system, including product quality, discount quality, review trust, coupon complexity, and usefulness signals.
- Build ML/AI models and rules-based intelligence to detect fake discounts, inflated list prices, low-quality products, suspicious reviews, and stale deals.
- Develop recommendation and ranking logic for Hot Picks, All Picks, Amazon Finds, and supporting filters.
- Work with LLMs to generate plain-English explanations such as Why it stands out, What to watch, and Why now.
- Create pipelines for product ingestion, enrichment, scoring, re-scoring, and freshness checks.
- Help define experimentation frameworks to compare deal scoring versions and improve user engagement.
- Collaborate with product, design, and business stakeholders to make AI outputs understandable and trustworthy to everyday shoppers.
- Support future personalization features such as user-specific deal recommendations, preference learning, and behavioral signal analysis.
Required Qualifications
- 5-6+ years of experience in AI, ML, data science, or applied machine learning engineering.
- Strong experience with Python and modern ML/data tooling.
- Experience building ranking, scoring, recommendation, classification, or fraud/spam detection systems.
- Practical experience with LLMs, embeddings, prompt engineering, or explanation generation.
- Strong understanding of data pipelines, APIs, databases, and backend integration.
- Ability to balance statistical modeling with practical business rules.
- Comfort working in a startup environment where speed, iteration, and product sense matter.
Nice to Have
- Experience with e-commerce, affiliate marketing, deal platforms, price intelligence, product search, or marketplace data.
- Experience with vector databases, semantic search, recommendation engines, or user personalization.
- Familiarity with Amazon product data, product feeds, review analysis, or pricing/coupon behavior.
- Experience with Supabase, Vercel, serverless architectures, or modern full-stack workflows.