Member of Technical Staff — RL Research (New PhD Grad)

Location: In-person in Seattle, five days a week

Salary: $250,000–$350,000 base salary per year, plus meaningful equity

Company

hirify.global is a research company building photorealistic, real-time AI avatars with emotional intelligence and full-duplex audiovisual interaction.

What you will do

• Build the RL and post-training stack from 0→1 and scale it from 1→10, including rollout generation, policy optimization, reward and reference model serving, evaluation, checkpointing, and observability.
• Develop post-training methods including PPO, GRPO, DPO, rejection sampling, RLHF/RLAIF, online RL, and model-based data improvement.
• Design systems abstractions connecting research ideas to production-scale training runs, including trainers, rollout workers, evaluators, data queues, experience buffers, and checkpoint promotion.
• Build feedback and evaluation loops for turn-taking, interruption, timing, emotional response, audiovisual coherence, instruction following, and real-time interaction quality.
• Optimize rollout throughput, serving latency, GPU utilization, policy updates, queueing, checkpointing, and research iteration speed.
• Evolve the platform as algorithms, model architectures, reward definitions, data sources, and evaluation methods change.

Requirements

• Completed or near-completion PhD in ML, RL, or a related field, demonstrated through publications, a strong lab or advisor, or substantial open-source work.
• Strong understanding of policy optimization, reward modeling, preference optimization, rejection sampling, KL control, evaluation, and data feedback loops.
• Ability to analyze reward hacking, unstable rewards, distribution shift, stale policies, mode collapse, over-optimization, noisy preferences, and evaluation mismatch.
• Exposure to RL or post-training pipelines through research, internships, or open source, with frameworks such as verl, ms-swift, OpenRLHF, or equivalent, and familiarity with rollout serving systems such as vLLM.
• Strong software engineering fundamentals and willingness to build reliable systems rather than prototypes only.
• Visa sponsorship is available from day one, including O-1, H-1B, and green card support.

Nice to have

• Experience with omni or multimodal post-training for audio-video-language models, especially long-context or real-time interactive systems.
• Experience with PPO, GRPO, DPO, online RL, RLHF/RLAIF, reward modeling, preference data, synthetic data generation, or model-based data improvement.
• Prior 0→1 experience building post-training systems, RL pipelines, agent training systems, evaluation platforms, or model improvement loops.
• Experience with distributed pretraining, data infrastructure, inference serving, simulation, feedback collection, or evaluation infrastructure.
• Publications or substantial open-source contributions in RL, post-training, alignment, evaluation, ML systems, or model behavior.

Culture & Benefits

• Research-focused environment working on unsolved problems in real-time, full-duplex AI.
• Meaningful equity designed for long-term ownership.
• HSA health plan with approximately $2,000 in annual company contributions.
• 15 days of PTO, public holidays, and a full week of office closure at year-end.
• Weekday lunch, drinks, snacks, commuter benefits, and a 401(k) plan.
• AI-native tooling with unlimited tokens.