Applied AI Researcher, Post-Training
Develops and evaluates post-training techniques like supervised fine-tuning, RLHF/DPO, and continual adaptation to align foundation models with enterprise systems. Requires expertise in adapting LLMs/SLMs, compound AI systems, and strong prototyping skills.
About the job
Key Responsibilities
- Adapt foundation models to real-world performance and alignment requirements using supervised fine-tuning, preference optimization (DPO, RLHF, RLAIF), and continual adaptation.
- Develop and evaluate techniques to align models with enterprise systems.
- Investigate methods for aligning large models with human and system-level objectives.
- Explore trade-offs between generalization and specialization, data efficiency and robustness, capability and controllability.
Requirements
- Deep understanding of post-training techniques: supervised fine-tuning, preference optimization (RLHF/DPO), LoRA/PEFT, instruction-tuning pipelines.
- Experience adapting frontier models (LLMs/SLMs) to specialized domains via data curation, reward modeling, or continual pretraining.
- Expertise in compound AI systems, agentic collaboration (ensembling, ReAct, graph-of-thoughts).
- Proven research track record (publications, public work).
- Daily use of AI tools (ChatGPT, Cursor, Perplexity).
- Strong programming and data analysis skills for prototyping and experiments.
What We Offer
- Base salary: $150K–$250K (depending on experience, location, level).
- Equity, comprehensive benefits: 100% covered medical/dental/vision, 401(k), commuter benefits, in-office lunch.
- Access to state-of-the-art models and AI tools.
Skills
RLHF, Dpo, Rlaif, Lora, Peft, Supervised Fine-Tuning, Instruction Tuning, LLMs, Slms, React, Graph-Of-Thoughts, Data Curation, Reward Modeling
Similar jobs
AI Research jobs
AI Digest
Remote
Conduct research on long-horizon, multi-agent AI behavior by designing agent environments, analyzing large-scale data, and running experiments. The role requires strong research judgment, rapid execution, independence, and familiarity with current AI developments.
AI Digest
Remote
Build, optimize, and evaluate long-running and multi-agent AI systems, along with tools for monitoring and analyzing their real-world behavior. The role requires software engineering experience with coding agents, strong independence, and familiarity with current AI developments.
Counsel Health
New York, NYResearch Scientist developing and evaluating health-focused AI models, large language models, and agentic systems for clinical applications. The role requires advanced research experience, strong coding skills, healthcare or clinical-data experience, and top-tier AI/ML publications.
Mercor
San Francisco, CA
Research Engineer focused on designing benchmarks, evaluation systems, rubrics, and failure-analysis workflows for frontier language models. The role requires strong applied AI research and coding experience, with expertise in model evaluation, data quality, and backend systems.
Hightouch
United States
Develops experimental AI techniques and prototypes for agentic marketing applications, with emphasis on image and video generation. The role requires strong backend or probabilistic systems expertise, quantitative thinking, creativity with LLM applications, and product intuition.