MTS - Agent Harness
About the role
Engineering role focused on polishing and building the browser agent harness to enable the Aside personal work agent to operate across web and desktop environments with optimized performance and real-world experimentation.
Responsibilities
- Polish our browser automation framework and memory system. You can make everything from the ground up, from the agent loop, compaction, memory to browser automation framework.
- Build an agent that uses your computer. Help Aside navigate browsers and desktop apps, understand what’s on screen, and complete tasks across them.
- Optimize our harness. Reduce token usage, work around bot detection, and experiment with heuristics that replace long prompt instructions with predictable behavior.
- Run real-world experiments. Build benchmarks and evaluation environments to test changes, catch regressions, and understand where the agent still fails on real tasks.
- Build with users. Talk to them, understand where the agent falls short in their work, and turn their feedback into shipped improvements.
Qualifications
- Use your brain. No benchmaxxing or autoresearch. You read the code and prompts yourself, make changes line by line, and understand why each change helps.
- An obsession with optimization. You care about making the agent more capable while reducing latency and cost. You track down wasted tokens and unnecessary steps, and measure whether your changes help.
- Systems rigor. You understand how Chrome DevTools Protocol, Playwright, and accessibility trees work, and know how to put them to use.
- Platform thinking. You think in primitives, not just features. You build solutions that solve today’s product needs while supporting future use cases.
- Proactivity. You create your own tasks. When something breaks or feels below the bar, you propose a solution and ship the improvement as if the product were your own.
Skills
Benefits
- Office in San Francisco
- Housing support (co-living house)
- Visa assistance (depends on the situation)
About Aside
Sales call cheating AI for enterprise tech sales
Aside is an AI agent that gives sales reps suggestions during sales calls: what to ask, how to answer, and when to push for next steps. - Real-time suggestion: Guides reps live on calls with tailored prompts- what to ask, how to answer, and when to push. - Sub-second search from technical docs: surfaces precise answers from docs, Slack, CRM, and past calls in under 500ms. - AI notetaking: captures call highlights automatically, so reps focus on selling, not typing. - Shared memory: learns from every deal- remembers what worked and replays it as suggestions in future calls. Tech sales requires expensive coaching. Teams spend 1.5 hours per week and $2,000 per rep each year on tools like AI notetakers and LMS. Enterprises like AWS and Oracle require internal exams and hire solution engineers for $200K+ to answer technical questions. But these don’t solve the problem: reps still repeat mistakes, miss answers, and deals stall or fall through. Aside eliminates the need for sales coaching. It surfaces the best answers from top reps–pulled from Slack, HubSpot, and past calls–in under 500ms. One of our users recovered a $100K deal after handling objections with a use case surfaced by Aside.
More open roles at Aside
- MTS - Product4w agoHybrid (San Francisco) · Aside
- GTM2mo agoHybrid · Marketing
- MTS - Mobile Engineer (iOS)2mo agoHybrid (San Francisco) · Engineering
- MTS - Founding Designer2mo agoHybrid (San Francisco, CA) · Aside