About the role
You'll build RAG systems, eval harnesses, and agent workflows for clients across health, finance, and enterprise. We measure shipped accuracy and $/request, not benchmark scores.
Stack
PythonFastAPIpgvectorAnthropic / OpenAIvLLMModal
What you'll do
Build retrieval + reranking pipelines
Design eval harnesses with the client's domain experts
Operate prompt + model rollouts behind flags
Track cost and accuracy in dashboards
What you need
Have shipped at least one LLM product to real users
Strong Python and at least one of: FastAPI, vLLM, LangChain
Understand retrieval, chunking, and reranking deeply
Comfortable instrumenting cost
Nice to have
Vector DB tuning
Fine-tuning experience
ML platform background
Hiring process
30-min intro call
Eval-design conversation (60 min)
Take-home (4 hours, paid)
Team meeting + offer
Live · accepting briefs/lat 25.20 lon 55.27
rt-482·v1.0
Apply
Sendusyourstory.
Paste a resume link or attach a PDF. A short note on what you'd want from a Robotech engagement is more valuable to us than a cover letter.
Now booking
2 slots openAug '26
next kickoff · week 34
Availability · next 6 weeks
W32
W33
W34
W35
W36
W37
First reply< 24h
median · last 30d4h 12m
24hFirst reply
40+Platforms shipped
4.9★Client rating
SOC 2Ready