SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 150,000 - 200,000 / annual
Contra Labs is a human-centered AI lab focused on creative and multimodal outputs. The company builds industry-leading creative preference datasets that power benchmarking, evaluation, and post-training for leading AI models and applications. Work spans design, video, imagery, and beyond, with a mission to define what "good" looks like in AI-generated creative content.
In this role, you will own research projects end-to-end, translating ambiguous client questions into rigorous research designs. You will identify research directions, develop methodologies, write proposals, execute studies, analyze results, and produce insights that shape strategic decisions for Contra Labs and its clients.
Key responsibilities include:
**Research Direction & Proposals**: Translate client questions into clear research questions and study designs. Develop novel research proposals and methodologies from scratch. Identify promising new research directions and push the team toward unexplored ideas. Help define what Contra Labs should measure and build next.
**Evaluation & Data Methodology**: Design human-data collection strategies, evaluation protocols, rubrics, and annotation schemes. Develop prompt strategies for eliciting and evaluating model behavior. Determine appropriate sampling, evaluator selection, calibration, quality-control, and reliability methods. Design methodologies across creative and multimodal domains including design, image, video, and agentic workflows.
**Analysis & Insight Generation**: Analyze qualitative and quantitative evaluation data. Move beyond reporting results to explain patterns and implications. Synthesize findings into clear recommendations, research narratives, and new hypotheses. Produce client-ready reports, presentations, benchmarks, and research publications.
**End-to-End Project Ownership**: Independently own research engagements from scoping through final delivery. Work closely with project leads, creative experts, research engineers, and data/engineering teams. Maintain high research rigor and data quality while operating on fast client timelines. Support multiple concurrent projects at different stages.
**Client Work**: Work on research driven by real client problems and constraints. Participate in scoping and proposal development. Establish credibility with sophisticated AI/ML research teams. Collaborate with Strategic Project Leads on client delivery.
**Requirements**
- 3–5+ years of relevant research experience
- Master's, PhD, or equivalent industry research depth in HCI, Human-Centered AI, ML, design research, or related field
- Strong qualitative and quantitative research skills with experience in human evaluation, experimentation, data collection, UX/HCI, annotation, or model behavior research
- Proven ability to independently design and execute rigorous research, including deciding what data to collect and how to analyze it
- Ability to turn data and observations into new insights, research directions, and actionable recommendations
- Comfortable analyzing data with Python and/or SQL
- Strong written communication and ability to clearly explain methodological tradeoffs and research decisions
- Comfortable operating independently through ambiguity and balancing research rigor with startup speed and pragmatism
- Based in NYC, USA; in-office 5 days/week (Williamsburg)
**Bonus qualifications**: Familiarity with modern ML and generative AI systems; understanding of RLHF, post-training, preference data, and model evaluation; experience studying image, video, multimodal, creative, or agentic systems; experience designing prompts or systematically studying prompting/model behavior; experience with large-scale human-data or annotation programs; experience working directly with AI research or model teams; strong publication record or evidence of consistently generating original research ideas; startup/0-to-1 experience.
