Post-Training Research Scientist
- Location
- Remote
- Work model
- Hybrid
- Level
- Entry
Skills
About this role
Open navigation Expanded hamburger menu for Two Sigma's site navigation Close navigation Search for Clear search About Us Businesses Investment Management Securities Real Estate Sightway Capital Insights Topics Data Science Engineering Markets & Economy News & Culture Careers Internships Engineering Quantitative Research & Data Science Open Roles Contact Us Investor Hub
Careers Portal
Career Portal
Open Roles
Events
Post-Training Research Scientist
Location
NY New York
United States
Business
Investment Management
Function
Quantitative Research
Experience Level
Experienced
Position Summary
Two Sigma is a leading quantitative investment management and trading firm. The company applies a scientific approach to investing, combining cutting-edge technology, artificial intelligence, data science, and quantitative research with rigorous human inquiry to capitalize on market opportunities and deliver alpha for investors. Our team of engineers, quantitative researchers and data scientists looks beyond the traditional to test hypotheses and develop creative solutions to some of the world’s most complex economic problems.
We are applying large language models and transformer-based architectures to problems where ground truth is delayed, noisy, and non-stationary. Our systems generate code, run experiments, and iterate autonomously, and we are looking to go beyond supervised fine-tuning. We are hiring a Post-Training Research Scientist to build RLHF, DPO, and reward modeling capabilities from the ground up. This is a greenfield role: you will define the infrastructure, research agenda, and evaluation frameworks for aligning LLMs to sophisticated, multi-step workflows in a domain where the reward signal is fundamentally different from existing research on human preference or deterministic task completion. This hire will help own methodology across training, fine-tuning, context management, and model evaluation. You will shape not only the post-training capability but the broader research direction of the team.
You will take on the following responsibilities: Lead post-training efforts for LLMs applied to financial time series and quantitative reasoning Design and execute RLHF, DPO, and related alignment methods at scale, including deployment of substantial compute budgets (O($100mm)) Build infrastructure for preference data collection, reward modeling, and policy optimization on financial datasets Drive research agenda connecting post-training methods to quantitative finance applications Collaborate with quant researchers to define task distributions and evaluation frameworks Unblock production systems dependent on post-training capabilities You should possess the following qualifications: BS or equivalent work experience in Science, Technology, Engineering or Math (an MS is a plus). Minimum 1 year of experience required; 1-10 years of experience preferred (ideally 1-5 years) at a frontier AI lab (OpenAI, Anthropic, DeepMind, Meta FAIR, or equivalent) Shipped post-training systems in production: RLHF, DPO, RLAIF, or related methods Deep understanding of distributed training infrastructure: multi-node GPU clusters, training stability, checkpointing Track record managing large-scale compute: budgeting, experiment design, ablations Publications or demonstrated expertise in alignment, preference learning, or reward modeling Hands-on implementation skills: PyTorch/JAX, distributed frameworks (DeepSpeed, FSDP, etc.)
You will enjoy the following benefits: Core Benefits: Fully paid medical and dental insurance premiums for employees and dependents, competitive 401k match, employer-paid life & disability insurance Perks: Onsite gyms with laundry service, wellness activities, casual dress, snacks, game rooms Learning: Tuition reimbursement, conference and training sponsorship Time Off: Generous vacation and unlimited sick days, competitive paid caregiver leaves Hybrid Work Policy: Flexible in-office