Role Description
This role involves designing indexing, ranking, and evaluation pipelines that combine traditional IR methods with neural re-rankers. You’ll build scalable, low-latency search systems capable of serving massive text corpora with high relevance and reliability.
- Design and implement hybrid IR systems that blend traditional retrieval methods with neural re-rankers.
- Build and optimize indexing and ranking pipelines using Elasticsearch/OpenSearch and FAISS.
- Develop neural re-rankers with Hugging Face Transformers and PyTorch.
- Combine BM25, TF-IDF, and neural models into hybrid search frameworks.
- Design and implement evaluation pipelines to benchmark retrieval performance.
- Optimize systems for low-latency performance at scale.
- Collaborate with researchers and engineers to integrate IR pipelines into production AI systems.
Qualifications
- Background in computer science, information retrieval, or data engineering.
- Proficient with Elasticsearch/OpenSearch for indexing and querying large text stores.
- Experience with neural search and reranking using FAISS, Hugging Face, and PyTorch.
- Understanding of traditional IR methods such as BM25 and TF-IDF and how to integrate them with modern ML approaches.
- Ability to design low-latency pipelines that serve results efficiently at scale.
- Comfortable working with pandas for data analysis and building evaluation workflows.
- Experience integrating pipelines into systems via REST APIs.
Requirements
- Passion for search, large-scale systems, and the intersection of IR and machine learning.
Benefits
- Part-time (20–30 hrs/week) with flexible hours—work from anywhere, on your schedule.
- Weekly Bonus of $500–$1000 USD per 5 tasks.
- Remote and flexible working style.
Why This Role Is Exciting
- You’ll shape the next generation of search and retrieval systems.
- You’ll apply both traditional IR methods and state-of-the-art neural re-rankers.
- You’ll work on massive-scale text datasets with real-world impact.
- You’ll operate at the intersection of search, machine learning, and large-scale systems engineering.
Pay & Work Structure
- You’ll be classified as an hourly contractor to Mercor.
- Paid weekly via Stripe Connect, based on hours logged.
Apply Now