About Consensus

Consensus is an AI search engine for scientific research. We use LLMs to help millions of users find and analyze research papers, easily. Our Series A was led by USV, with major participation from top AI investors like Nat Freidman and Daniel Gross. Consensus has been featured in The Wall Street Journal, The Atlantic, The New York Times, Nature, and a16z as one of the most exciting new AI search engines in the world.

Our mission is to make expert knowledge discoverable and consumable for all. Help us build the future of research.

Responsibilities

• Improve search relevance and query understanding via ranking models, feature engineering, and ML model integration
• Build dashboards and tools for evaluating search relevance and engagement metrics
• Manage search infrastructure, optimize latency, and reduce costs
• Develop search data pipelines for downstream relevance and ML tasks
• Contribute to general full stack web development supporting search, user-facing features, and other team needs

Must Haves

• 5+ years of software engineering experience
• 3+ years of search relevance and NLP experience, including experience with semantic search, learning-to-rank, and modern NLP techniques
• Strong experience with Python

Nice to Haves

• Strong experience with ElasticSearch
• NLP and ML libraries, like XGBoost, NLTK, spaCy, and scikit-learn
• Distributed data processing frameworks like Spark, Dataflow, Flink, or Dask
• Data analysis and visualization libraries, such as pandas, numpy, scikit-learn, seaborn, plotly, etc.
• Knowledge Graphs
• Web Crawling
• Experience constructing domain-specific golden sets, especially in science and medicine domains
• Other generalist full stack engineering skills

Why You’ll Succeed:

• Attention to detail and craft.
• Track record of high velocity delivery.
• Interest in science, research, and LLMs.