sgondala_ycapp
Joined 4 years ago
Joined 4 years ago
Initially, we didn’t include an "Other" category - which led the LLM to force-fit documents into existing types even when they didn’t belong. Obv this wasn't LLM's fault.
We realized the mistake and added "Other". This significantly improved output accuracy!
At FurtherAI, we're creating vertical AI agents to automate tasks traditionally done by humans. We recently raised a seed round from top investors (announcement soon), growing rapidly, and are looking for superstars to join us on our journey
We are hiring for three roles:
1. Backend/Full Stack Engineer: https://www.ycombinator.com/companies/furtherai/jobs/YZZvimn...
2. Founding Applied Research Engineer: https://www.ycombinator.com/companies/furtherai/jobs/MCLEvo5...
3. Frontend Engineer (Web): https://www.ycombinator.com/companies/furtherai/jobs/zrN2j29...
Apply on the URLs or email [email protected] with your resume, github, and the most impressive thing you've built.
At FurtherAI, we are building a workforce of AI Teammates to automate insurance workflows involving processing unstructured documents, data entry into internal systems or web portals, or even making phone calls.
Our core mission is to answer a critical question: Can AI be made as reliable, adaptive, and continuously learning as a new human employee?
Our founding team features a second time founder and a language modeling scientist from Apple. We have raised a pre-seed round from top-tier investors, including Y Combinator, South Park Commons, and Converge VC.
We're looking for exceptional software and backend engineers to join our founding team. You'll play a pivotal role in building the core product while also spearheading efforts to ensure scalability, optimize performance, and continuously improve the product to meet evolving needs and challenges.
If you're excited about working at the intersection of AI agents and workflows, we'd love to hear from you.
For more information and to apply - https://www.ycombinator.com/companies/furtherai/jobs/YZZvimn...
I'm approaching scheduling first - looking at your calendar and coordinating with others to find availability and setting up a meeting - all by just invoking the model.
Eventual goal is to do everything a real human assistant can do online + over phone calls.
Just starting off, and would love to talk to more people interested in this domain. Feel free to hit me up at [email protected]
We're building the AI agents that run insurance - a $1T+ industry still run on PDFs, email, and manual review. Our agents read the documents, pull from the systems underwriters already use, and actually complete the work. In production at top-10 carriers and F100 brokers; ~10x growth in the last year; backed by a16z and YC.
The hard problems: keeping an agent reliable across dozens of tool calls; orchestration + evals + reliability on top of frontier models.
We've rebuilt the product from scratch more than once as the models got better!
Stack: Python, TypeScript/React, Azure, frontier LLMs.
Roles (all onsite SF): - Staff AI Engineer — agent reliability, evals, orchestration ($250–350K + equity) - Staff Product Engineer — full-stack, own the product surface ($250–350K + equity) - Staff Infrastructure Engineer — Azure, single-tenant, SOC 2 ($250–350K + equity) - Founding Product Manager — technical, first PM ($180–230K + equity)
Email me (co-founder/CTO): [email protected]