Dear Anthropic Talent Acquisition team,
I would like to be considered for the AI Engineer role listed on your careers page. AI engineering has been at the center of my work for the past few years, and I would be glad to bring it to your team.
Ahead of writing I looked into Anthropic, and what grabbed me was your work on retrieval-augmented assistants and the engineering posts your team keeps sharing on grounding LLMs in real data. It feels like a great point to come aboard, and I would gladly turn my AI engineering experience to it.
Reading the posting, the three areas you weigh most are LLM application development, RAG and vector search and prompt engineering and evaluation. Those decide whether an AI hire pays off, and I have real results in each.
On LLM application development, I work with Python, LangChain and the OpenAI API. As an AI Engineer at Perplexity, I built a RAG assistant over 2M internal docs that cut support resolution time by 40%. On top of that, I built the shared prompt library the whole product team now works from.
For RAG and vector search, I rely on embeddings, pgvector and reranking. In my time as an AI Engineer at Perplexity, I shipped a hybrid retrieval layer that raised answer accuracy from 71% to 92%.
On prompt engineering and evaluation, I bring eval harnesses, prompt versioning and guardrails. Working as an AI Engineer at Perplexity, I set up an evaluation harness that caught prompt regressions before they reached users. On top of that, I wrote the guardrail policy the whole team follows.
I would gladly take you through any of this in an interview and lay out why I fit. I am ready to ship AI features that hold up, help the team move quickly, and keep growing with it.
Thanks for reading, and I hope we can arrange a time to talk.
Yours sincerely,
Theo Script
theo.script@gmail.com