About Forward
Forward is a consulting firm that works exclusively with independent consultants to help startups build their engineering organizations.
About the Work
Keywords: Manual QA, LLMs
Budget: $3.5-$5k/month
Hours per week: 40
Term: 3-6 months with possibility of extension
Geographic Constraints: Latam based candidates preferred
Timezone Constraints: 6 hours overlap with ET
Start Date: Immediate
Company Stage: Series A
Context:
We’re working with a company that is streamlining the workflows of insurance companies using AI. They have a 10+ step, LLM-based workflow that ingests large amounts of numerical data and produces a summary of that data for stakeholders at an insurance company.
They are constantly making adjustments to this workflow - tweaking prompts, adding or removing steps, introducing LLM-based quality checks on output - and they need someone to help them understand whether the changes they’re making to this workflow are improving the quality of its final output.
This role will involve working with stakeholders in product to align on quality metrics and continuously comparing the final outputs of different versions of workflow against a stable set of inputs.
Prior experience with AI and LLMs is great but is not a hard requirement for this role.
About You
Roughly in order of importance:
- You have manual QA experience
- You have experience managing and creating scripts for a manual QA process
- You have experience working directly with stakeholders outside of QA
- You have 3+ years experience
If this role sounds interesting to you, we’d love to hear from you here.
Research shows that certain folks are less likely to apply for work when they don’t meet 100% of the outlined qualifications. If this role excites you, we want to hear from you. If not and you’re looking for contract work, feel free to reach out to us or take a look at our other roles. You can also view our privacy policy here.