Job Description

This role is on-site M-F in the Flatiron District - New York City, NY. 

Our client is a Series A point-of-sale software company in NYC. 

They move fast and ship daily. AI-assisted engineering isn't a talking point here; agents like Devin, Claude, and Codex are part of how the team works every day, and engineers who master that leverage ship multiples of what they could alone.

About the Team

Applied AI owns the intelligence layer, including aspects of Merchandising , Custom Reporting, Ecommerce, and Agentic workflows.  

This is the team behind our AI Manager — a suite of production agents that handle end-to-end workflows like retail pricing strategies, creating marketing campaigns, maintaining SEO (eCommerce) and developing custom reports that give store owners the insight they need to run a stronger business. This team also owns invoice OCR/CV (structured extraction from messy distributor invoices, with selectable LLM engines) and embedding-based product matching. Nothing here is a demo: every model output lands in front of a real store owner making a real pricing decision.

About the Role

You'll design, build, and iterate on the agents powering our core merchant experience. Working on this mission-critical team, you'll develop production agent and context-layer applications — turning each store's sales history, catalog, and market context into decisions that make independent retailers money. You'll own your models from research to production, and your work ships into stores the same week.

In this role, you will

• Apply state-of-the-art ML and LLM techniques to problems spanning:
• Merchandising intelligence (slow-mover detection, price and promotion recommendation, competition and seasonality signals);
• Document understanding (invoice OCR and structured extraction across LLM engines);
• Retrieval and ranking (embedding-based product matching on pgvector, catalog dedup, contextual recommendations)
• Build agent capabilities on top of our Manager Agent platform — task generation, review workflows, and chat over each store's own data
• Build the evaluation harness for both offline and online techniques, designing experiments and metrics (evals, QA playbooks, Langfuse tracing) that provide deep insight into recommendation quality and merchant impact
• Own the entire model lifecycle from research to production: data analysis, modeling, evaluation, offline/online testing, and iterative improvement — and build autonomous harnesses that let agent squads explore new problem spaces in parallel
• Collaborate cross-functionally with engineers, PMs, and store owners to ensure our AI drives measurable improvements in merchant revenue and hours saved
• Stay at the forefront of ML/AI innovation by evaluating and incorporating emerging research, models, and techniques into the product lifecycle

Your background looks something like this

• 5+ years building and shipping robust AI products for large-scale, user-facing or data-driven products
• Strong software engineering skills (TypeScript and/or Python, production-quality codebases, collaborative development) and experience using agentic coding tools for large-scale parallel development
• In-depth experience with the full AI lifecycle: data analysis, rigorous evaluation, and ongoing monitoring and improvement
• Proven collaborator and communicator; excels in high-velocity, cross-functional teams
• Curious, driven by end-user and product impact, and passionate about advancing the state of applied ML and AI
• BS, MS, or PhD in Computer Science, Engineering, or a related field (or equivalent experience)

Even better

• Experience with LLM context engineering or harness engineering
• Experience in mid-training or post-training frontier open-source models
• Experience with large-scale user-centric and content-centric personalization challenges (user modeling, retrieval, content ranking)
• Experience with LLM observability and eval tooling (Langfuse or similar) in production
• Familiarity with our stack: Next.js, tRPC, Prisma, PostgreSQL with pgvector, Vercel
• Retail, pricing, or demand-forecasting domain experience — you know why moving a slow SKU matters to a store's cash flow

Compensation

$220k – $300k + Meaningful equity

This range reflects the expected compensation for this role. Compensation within the range is determined based on experience, skills, and scope of responsibilities. In addition to base salary, we offer meaningful early-stage equity — this team's work is the foundation the company compounds on. Bonuses can be upward of 50% of base salary based on personal and company performance as well. 

Benefits

• Fully company-covered medical and dental benefits.
• 401(k)
• Catered Lunches and Dinners: We provide dinner each evening for employees who would like to eat and connect with the team. Lunch is provided on a weekly basis.

#ZR

Job Tags

Similar Jobs