Software Engineer, RL Data
The Software Engineer on the RL Data team at Confidential Client is responsible for designing and iterating on task sets, rewards, and environments that train coding agents using reinforcement learning. This role involves analyzing agent behavior data to identify failure modes, improving data quality, and collaborating with research teams to ensure datasets effectively teach desired capabilities, contributing to the automation of coding through innovative engineering and research.
About Careertakes
👉 Important disclosure: Careertakes is a third-party recruiting platform supporting this hiring process. If selected, you will be employed directly by our client, Software Development.
Applicants for this role may also receive access to additional matched opportunities through the Careertakes platform.
What You’ll Do
As a Software Engineer on the RL Data team for our confidential client, you'll design and ship the datasets, tasks, rewards, and environments that train production coding agents. You’ll work cross-functionally with research and engineering to convert messy agent behavior into reusable, high-quality training signal.
- Design task sets and evaluation loops that teach concrete agent capabilities, iterate from traces and evals until performance improves
- Analyze agent traces to identify failure modes and build tooling or datasets that surface and address those issues
- Convert one-off recipes into reusable infrastructure: improved rewards, cleaner environments, and higher data quality
- Partner closely with research to validate whether datasets are teaching the intended behaviors
- Build systems and pipelines that scale data collection, labeling, and evaluation for RL training
Qualifications
- Strong software engineering fundamentals — you write careful, efficient, well-tested code
- Experience or comfort with infra, data, or distributed systems
- Ability to break fuzzy capabilities into measurable tasks and concrete metrics
- Enjoys working with noisy real-world agent traces and converting them into datasets or tools
- Bachelor’s degree (per client posting) or equivalent practical experience
Nice to Have
- Prior exposure to reinforcement learning concepts or RL pipelines (helpful but not required)
- Experience collaborating with research teams to validate datasets and metrics
- Background in producing reliable, large-scale training data or evaluation tooling
Why Join
- Work on cutting-edge products that scale RL on real user data to improve coding agents
- Small, talent-dense teams with a high-impact, fast-moving environment
- Opportunities to influence research + engineering workflows and ship production solutions
Additional Details
- Employment type: Full-time
- Location: San Francisco, CA (on-site or hybrid per client policies)
- Education: Bachelor’s degree or equivalent (listed by client)
Equal Opportunity & Hiring Transparency
Careertakes and our client are Equal Opportunity Employers committed to building a diverse and inclusive workforce. We prohibit discrimination or harassment of any kind. To support a fair and efficient hiring process, AI tools may be used to assist with application review or resume screening. These tools do not replace human decision-making. Final hiring decisions are made by people.
If you have questions about how your data is used, please contact us directly.
Negotiate a higher salary! Check the salary ranges for this job type in your area.
View My Salary Range