Research Engineer, Post-Training (AI)

TL;DR

Research Engineer, Post-Training (AI): Scaling the post-training loop to transform expert feedback into high-performing models for legal work with an accent on model training experiments and reward systems. Focus on optimizing agent harnesses, designing reliable grading systems, and improving quality on long-horizon legal tasks.

Location: San Francisco

Salary: $231,000 – $340,000 USD (Offers Equity)

Company

hirify.global is an AI platform transforming legal and professional services by combining frontier agentic AI with deep domain expertise.

What you will do

• Drive post-training experiments to push agent performance while balancing cost, latency, security, and governance.
• Optimize agent harnesses, including domain-specific skills, retrieval strategies, and validation loops for long-horizon legal work.
• Design and develop reliable grading and reward systems for high-stakes legal evaluation and iteration.
• Analyze agent behavior to identify successful patterns and convert findings into training data, evals, or harness changes.
• Collaborate with internal and external research partners to define experiments and execute model improvements.

Requirements

• Hands-on experience with post-training or model-training (SFT, preference optimization, RLHF/RLAIF, reward modeling, distillation).
• Strong judgment regarding model behavior, including the ability to inspect traces, outputs, and identify failure modes.
• Strong Python and research-engineering ability to build reliable systems for faster research iteration.
• Ability to self-manage ambiguous applied research projects and communicate effectively with cross-functional teams.
• Must be located in San Francisco

Nice to have

• Experience building ML data or evaluation infrastructure, such as curation pipelines or experiment tracking dashboards.
• Experience with distributed training, inference systems, GPU workloads, or large-scale ML experimentation.
• Research publications, open-source contributions, or shipped industry work in LLMs and AI agents.

Culture & Benefits

• Competitive compensation including a high base salary and equity.
• Opportunity to contribute to a generational company at a true inflection point with strong product-market fit.
• High-intensity environment that values decisiveness, simplicity, and ownership.
• Collaborative culture working alongside world-class researchers and investors.