Research Intern, Together AI

• We’re looking for research interns who want to work on foundational questions in RL and post-training, grounded in realistic inference systems
• Are pursuing a PhD or MS in Computer Science, EE, or a related field (exceptional undergraduates considered)
• Have research experience in one or more of:
• RL or post-training for large models (e.g., RLHF, RLAIF, GRPO, preference optimization)
• ML systems (inference engines, runtimes, distributed systems)
• Large-scale empirical ML research or evaluation
• Are comfortable with empirical research:
• Designing controlled experiments and ablations
• Interpreting noisy results and drawing principled conclusions
• Can work across abstraction layers:
• Strong Python skills for experimentation
• Willingness to modify inference or training systems (experience with C++, CUDA, or similar is a plus)
• Care about research insight, not just benchmarks:
• You ask why methods work or fail under real system constraints
• You think about how infrastructure assumptions shape algorithmic outcomes

Desirable

• The Turbo Research team investigates how to make post-training and reinforcement learning for large language models efficient, scalable, and reliable
• Our work sits at the intersection of RL algorithms, inference systems, and large-scale experimentation, where the cost and structure of inference dominate overall training efficiency and shape what learning algorithms are practical
• As a research intern, you will study RL and post-training methods whose performance and scalability are tightly coupled to inference behavior, co-designing algorithms and systems rather than treating them independently
• Projects aim to unlock new regimes of experimentation—larger models, longer rollouts, and more complex evaluations—by rethinking how inference, scheduling, and training interact
• Intern projects are tailored to your background and interests, and may include:
• Inference-Aware RL & Post-Training
• Designing RL or preference-optimization objectives that explicitly account for inference cost and structure (e.g., speculative decoding, partial rollouts, controllable sampling)
• Studying how inference-time approximations affect learning dynamics in GRPO-, RLHF-, RLAIF-, or DPO-style methods
• Analyzing bias, variance, and stability trade-offs introduced by accelerated inference within RL loops
• RL-Centric Inference Systems
• Developing inference mechanisms that support deterministic, reproducible RL rollouts at scale
• Exploring batching, scheduling, and memory-management strategies optimized for RL and evaluation workloads rather than pure serving
• Investigating how KV-cache policies, sampling controls, or runtime abstractions influence learning efficiency
• Scaling Laws & Cost–Quality Trade-offs
• Empirically characterizing how reward improvement and generalization scale with rollout cost, latency, and throughput
• Quantifying when systems-level optimizations change algorithmic behavior rather than only reducing runtime
• Identifying regimes where inference efficiency unlocks qualitatively new learning capabilities
• Evaluation & Measurement
• Designing rigorous benchmarks and diagnostics for post-training and RL efficiency
• Studying failure modes in long-horizon training and how system constraints shape outcomes
• Our summer internship program spans over 12 weeks where you’ll have the opportunity to work with industry-leading engineers building a cloud from the ground up and possibly contribute to influential open source projects. Our internship dates are May 18th to August 7th or June 15th to September 4th

• Please submit your application with:
• Resume/CV
• A cover letter that includes your preferred research areas, academic transcript (unofficial is acceptable), and links to relevant projects or publications