G

Senior Research Engineer – AI Agent Systems (Post-Training & RL)

United States
Visa Sponsorship
This Job is No Longer Active This position is no longer accepting applications

Join Goaly AI as a research-engineering leader to design and optimize AI agent systems, focusing on reinforcement learning, post-training experiments, and scalable model improvements. You’ll bridge research and engineering, improving infrastructure, data pipelines, and agentic capabilities like tool use, reasoning, and long-horizon task completion. Requires strong Python, deep learning, and RL expertise with hands-on experimental rigor.

Key Highlights
Own the experimental loop for transforming base models into capable agents (RL, tool use, coding, planning).
Design data pipelines, environments, and evaluations with reproducibility and reliability as priorities.
Collaborate cross-functionally to debug infrastructure, optimize training pipelines, and translate research into production.
Key Responsibilities
Design and execute post-training experiments for agentic capabilities (tool use, coding, reasoning, long-horizon tasks).
Build realistic RL environments, task harnesses, and evaluations with robust reward signals and telemetry.
Develop data pipelines for training/evaluation, ensuring contamination control, difficulty balancing, and reproducibility.
Analyze model behavior for failure modes (reward hacking, mode collapse, distribution gaps) and iterate on training recipes.
Improve research workflows by enhancing experiment configuration, rollout inspection, and automated comparison tools.
Partner with systems engineers to debug cross-layer issues in rollout inference, distributed training, and data movement.
Translate successful research into stable, production-ready pipelines and contribute to the team’s long-term roadmap.
Technical Skills Required
Python Reinforcement Learning Deep Learning
Benefits & Perks
Hybrid work (4+ days/week in Palo Alto)
Visa sponsorship (H-1B, OPT/CPT)
Complimentary meals and snacks
Nice to Have
Experience with RLHF, reinforcement fine-tuning, or preference optimization.
Familiarity with PyTorch/JAX and distributed ML frameworks (FSDP, Megatron, Ray, VeRL).
Record of influential research, open-source contributions, or production model launches.

Job Description

Goaly is a stealth AI startup founded by ex-Meta MSL engineers and researchers. Our mission is to dramatically lower the cost, time, and talent barriers to building proprietary AI — and make each generation of models faster and cheaper to build than the last.Backed by leading AI investors and endorsed by frontier AI researchers and builders, we’re looking for exceptional new grads who want to work on hard, foundational AI systems problems with outsized ownership from day one.
Want the full job description? Read the complete details on LinkedIn, the original posting.
Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.

See Jaabz jobs first on Google 1 tap · free · in AI Overviews Jaabz is on your Google Manage Preferred Sources
Keep exploring

Similar Jobs

Explore other opportunities that match your interests

Visas, Work Permits & Legal Insights

Stay informed about visa types, work permits, and immigration updates for international professionals.

Browse all articles

Subscribe to our newsletter

New visa sponsorship, relocation and remote tech jobs, delivered to your inbox.