AI Engineer – Agentic Systems & RAG - Looking for an experienced AI Engineer to design and build our next generation of agent-powered products. In this role, you’ll develop, evaluate, and scale sophisticated Retrieval-Augmented Generation (RAG) pipelines and agentic workflows that unlock new, intuitive ways to shop.
Our LLM-powered agents leverage a rich set of tools to interact with customer catalogs, perform advanced retrieval, and guide users through browsing and discovery. The result: accurate, well-cited answers and exceptional product recommendations for open-ended user queries.
What You’ll Do
- Design and implement real-time, agentic workflows that handle complex, multi-step user tasks and open-ended queries
- Build systems that deliver accurate, context-aware responses and high-quality product recommendations
- Own the end-to-end data lifecycle for AI workflows, including vector ingestion, indexing, and retrieval
- Define and implement evaluation metrics to measure relevance, performance, and alignment with business and user goals
- Rapidly prototype and validate new product ideas using LLMs, RAG, and agent-based systems
- Collaborate closely with Product, Design, Analytics, and Engineering partners to turn AI capabilities into polished product features
- Continuously improve the speed, quality, reliability, and efficiency of our AI systems
- Take ownership of systems from initial design through deployment, monitoring, and long-term maintenance
What We’re Looking For
- 4+ years of industry experience in areas such as search, information retrieval, recommendation systems, applied ML, or NLP
- Strong ability to communicate technical work in terms of business impact
- Proficiency in Python and SQL, with hands-on experience building end-to-end ML or LLM-powered systems
- Deep understanding of information retrieval techniques (e.g., dense retrieval, re-ranking, chunking strategies)
- Practical experience building Retrieval-Augmented Generation (RAG) systems; experience with autonomous agents is a strong plus
- Familiarity with ML evaluation methodologies and core IR metrics
Nice to have:
- experience with automated prompt optimization techniques (e.g., DSPy)
- A product-oriented mindset, strong ownership mentality, and passion for shipping high-quality work
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 & Perks
- Unlimited vacation time (we encourage everyone to take at least 3 weeks per year)
- Fully remote team, work from anywhere
- Work-from-home stipend to support your home office setup
- Apple laptop provided
- Annual training and professional development budget
- Maternity and paternity leave for eligible employees
- Regular team offsites to connect and collaborate
- Work alongside smart, supportive teammates and make a meaningful impact
Compensation:
This role has a base salary range of $80,000–$120,000 USD, depending on experience, skills, and interview performance.
Email a friend
Report this Job