Software Engineer, Data Enrichment (Backend)

Stylitics

48d

About The Position

Stylitics is a retail AI platform powering real-world, repeatable success for dozens of enterprise retailers. More than 100 million shoppers each month engage with our AI-driven outfitting, product discovery, and personalization experiences across e-commerce, apps, email, and stores. What sets us apart isn’t just what our AI can generate but the 10+ years of retail data, workflows, tools, experts, and QA systems behind it. These are the mission-critical components required to deliver safe, brand-right, production-ready AI at scale. Retailers trust Stylitics to elevate customer experience, drive revenue, and bring proven AI use cases to life.

We're building the future of AI-powered fashion & retail automation, and we need a craftsperson who lives and breathes Clojure.

We have AI workflows that transform basic product data into rich, structured, search-optimized content, powering everything from Google Merchant feeds to SEO-ready PDPs to machine-readable data for generative AI search engines. This enriched catalog data must flow reliably to 175+ enterprise retailers at scale. All of it needs to be fast, accurate, and integrated into our existing platform serving 100M+ shoppers monthly.

You'll work in Clojure and ClojureScript across the stack, but this is backend-heavy. You'll own features end-to-end: from data pipeline architecture to enrichment APIs to the tools your colleagues use to validate and ship enriched catalogs daily.

We're a team of 12+ Clojure engineers who move fast and care about craft. We value ownership deeply. You'll have autonomy to architect solutions, make technical decisions, and ship production code quickly. If you're curious, opinionated about good code, and excited to build AI-powered data systems that drive real retail performance at scale, keep reading.

Requirements

• Bachelor's Degree from an accredited college or university in Computer Science, Software Engineering, or other related fields
• Confident communication (written and oral) skills and a demonstrated ability to work collaboratively with all levels of internal and external organizations
• Strong problem-solving, attention to detail, organizational, and time management skills along with demonstrated strategic thinking abilities
• Strong Clojure foundation. You've built production systems, you understand functional programming deeply, and you're comfortable with the ecosystem
• Solid SQL skills and database design experience. You can model complex domains in PostgreSQL, write efficient queries, design schemas, and handle migrations
• Experience integrating LLMs into production systems. You understand prompt engineering, managing context windows, handling non-deterministic outputs, and the practical challenges of building reliable AI features
• Backend engineering fundamentals. You know how to build APIs, design data flows, handle errors gracefully, and architect systems that scale
• High velocity. You ship often. You balance speed with quality, you know when to refactor and when to iterate, and you don't let perfect be the enemy of good
• Ownership mindset. You take responsibility for features from conception to production. You care about the outcome, not just writing code
• Curiosity. You're interested in AI, workflow orchestration, vector search, frontend UIs, data modeling, and figuring out how all the pieces fit together

Nice To Haves

• Experience at a high-growth start-up and comfortable with the unknown.
• Experience in front-end development, and with ClojureScript
• Experience with Java and the JVM ecosystem
• Experience with Temporal or similar workflow orchestration systems (Airflow, Dagster, Step Functions)
• Familiarity with vector databases like Qdrant, Pinecone, or Weaviate, and RAG architectures
• Experience with MCP (Model Context Protocol) or building tool-calling systems where LLMs interact with external services
• Background in product catalog systems, taxonomies, or PIM platforms
• Familiarity with SEO, structured data (schema.org), or feed management (Google Merchant Center)
• Experience with large-scale data transformation, normalization, or data quality pipelines
• Contributions to open-source Clojure projects
• Background in other functional programming languages (Haskell, OCaml, Elixir, Scala)
• Experience building developer tools, automation systems, or human-in-the-loop workflows

Responsibilities

• Temporal workflows that orchestrate multi-step AI operations: product attribute extraction, description generation, metadata enrichment, and feed optimization for Google Merchant Center and other shopping networks
• Backend services in Clojure that integrate with LLM APIs (GPT, Gemini, etc.) to enrich product catalogs, extracting style, occasion, and trend attributes, generating SEO-optimized copy, and producing structured schema markup at scale
• Data models and PostgreSQL schemas that support complex enrichment pipelines, product taxonomies, attribute hierarchies, and integration with retailer catalog systems
• RAG pipelines using Qdrant for semantic search, product similarity matching, and context retrieval that powers more accurate attribute inference and enrichment suggestions
• APIs and data pipelines that deliver enriched catalogs to retailer PDPs, shopping feeds, and search engines, plus monitoring systems that track enrichment quality, coverage, and downstream performance

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level