Agent Post-Training, Connectors Research
Core
Train frontier AI agents to interface with professional software, APIs, and tools (e.g., Slack, GitHub, Salesforce) to execute multi-step workflows and operate across a user's digital context.
Role type
Senior IC machine-learning engineer (agent post-training)
Builds
Training signals, evals, environments, and feedback loops for agentic model behavior in production systems.
Domain
AI research, machine learning, software engineering, enterprise productivity tools
Deliverable
production ML models
Required skills
machine learning fundamentals, LLMs, RL/RLHF/RLAIF, post-training, evals, graders, synthetic data, model training, coding agents, tool-using agents, production ML systems
Preferred skills
research taste, engineering execution, cross-functional collaboration, hypothesis-driven experimentation, building load-bearing systems
Technologies
RL, data pipelines, graders, reward signals, evals, diagnostics, synthetic data, multi-agent systems
Responsibilities
Design and run experiments to improve agentic model behavior for complex software; own end-to-end improvements to the post-training stack; build evals and environments to expose model failures; partner with product teams to translate user needs into model improvements; work on early-training and alignment interventions; decide which integrations are ready for major model runs; improve large-scale training machinery; debug hard failures in shipped models.
Seniority
Senior, hands-on IC
