About Us
Constructor is a U.S. based company that has been in the market since 2019, building a next-generation platform for search and discovery in ecommerce. Its search engine is entirely invented in-house, utilizing transformers and generative LLMs, and powers over 1 billion queries every day across 150 languages and roughly 100 countries.
Responsibilities
- Architect and build real-time agentic workflows to handle complex, multi-step user tasks and open-ended queries, providing users with accurate and contextually relevant answers and product suggestions
- Own the end-to-end data lifecycle for AI workflows, including vector database ingestion and indexing
- Design metrics to evaluate the relevance and performance of query results, ensuring alignment with business goals and user expectations
- Generate and rapidly prototype novel product hypotheses that leverage LLMs, RAG, and agentic systems
- Collaborate closely with Product, Design, Analytics, and other engineering teams to translate AI capabilities into tangible, high-quality product features
- Improve the speed, quality, and efficiency of our AI systems and engineering processes
- Take ownership of systems and designs from conception through to deployment and maintenance
Qualifications
- 4+ years of industry experience in related fields, including search, information retrieval, recommendation systems, applied machine learning, and NLP
- Excellent skills in delivering and communicating business value
- Proficient in Python, SQL, and the big data stack for end-to-end ML product development, with experience across the entire pipeline in typical recommendation systems or LLM-based solutions
- Strong grasp of Information Retrieval (IR) techniques (e.g., dense retrieval, re-ranking, chunking strategies)
- Direct experience with Retrieval-Augmented Generation (RAG); experience building autonomous agents is a strong plus
- Nice to have: experience with automatic prompt optimization techniques (e.g., DSPy)
- Solid understanding of ML evaluation methodologies and key IR metrics
- Passion for shipping high-quality products and a self-motivated drive to take ownership of tasks
Tech Stack
- Core: Python, FastAPI, asyncio, Airflow, Luigi, PySpark, Docker, LangGraph
- Data Stores: Vector Databases, DynamoDB, AWS S3, AWS RDS
- Cloud & MLOps: AWS, Databricks, Ray
Benefits
- Unlimited vacation time – we strongly encourage all of our employees take at least 3 weeks per year
- Fully remote team – choose where you live
- Work from home stipend! We want you to have the resources you need to set up your home office
- Apple laptops provided for new employees
- Training and development budget for every employee, refreshed each year
- Maternity & Paternity leave for qualified employees
- Work with smart people who will help you grow and make a meaningful impact
- This position has a base salary range between $80k and $120k USD.
XML job scraping automation by YubHub
