Responsibilities
- Create scalable text processing pipelines for ingestion, cleaning, normalization, and tokenization to enable downstream NLP tasks.
- Design and manage indexing solutions and vector databases to support semantic search and retrieval capabilities.
- Develop standardized prompting methods and lead fine-tuning efforts for large language models specific to business use cases.
- Build intelligent, dynamic systems using LangChain and LangGraph to enable agentic workflows and knowledge orchestration.
- Implement advanced retrieval-augmented generation architectures, including VRAG and GraphRAG, to improve context accuracy and information retrieval.
- Evaluate and optimize NLP models through benchmarking and performance testing to enhance efficiency, scalability, and precision.
- Partner with engineering, product, and research teams to integrate AI-powered features into production environments.
- Lead technical direction by mentoring junior team members, promoting best practices, and advancing innovation across data science projects.
Compensation
Competitive salary based on experience, education, skills, and expertise; includes comprehensive benefits.
Work Arrangement
Fully remote, US-based with residency in EST or CST time zone
Team
Collaborative environment involving engineering, product, and research teams
Other
- Full-time permanent role requiring core business hours in your local time zone, with occasional adjustments to support global collaboration.
- Position is fully remote within the United States; candidates must reside in the Eastern or Central time zone.
- Compensation is determined by experience, education, technical skill, expertise, and other relevant qualifications.
- Eligible employees receive a comprehensive benefits package including health insurance, 401k with company match, disability coverage, paid time off, and additional perks.
Not mentioned
