London, UK

Be an owner and a valued thought partner. Join Portia AI!

Agents are still difficult to deploy at scale in Production environments but the industry agrees fixing them will unlock the future of AI. In Sam Altman’s words “Users will increasingly interact with systems…which can take actions on their behalf, rather than talking to a single model”. If this challenge speaks to you, there is no better place to shape the answer than Portia AI!

We are a seasoned (and possibly even fun) founding team with leadership experience in product and engineering roles at Amazon, Google and Stripe. We are backed by some of the best VCs out there including General Catalyst and First Minute Capital. We are looking to build a talented, nimble and meritocratic engineering team to execute on this. Would you like to be our Founding Engineer? Read on.

Our Mission

LLMs today have the ability to indicate that they want to consider one or many tools to answer a user’s prompt. As businesses start deploying LLMs at a larger scale in production environments, the tool calling layer will need to evolve to ensure that it can handle a variety of authentication mechanisms, can offer a wide and expandable library of tools, and can personalise the tools it provides to the LLM. Portia exists to solve those emerging challenges: We want to make it dead simple for developers to add secure and accurate tool calling to their AI deployments.

The role

You are ready to thrive in a fast paced environment and with a high degree of ambiguity. You want to be actively involved in helping to shape the future of the product and the company. As one of the first ML / AI engineers on the team, you are passionate about LLMs, developer infrastructure and experience. You are also excited to uplevel the broader team on what it takes to deploy a good, production-scale AI-powered product. Key requirements include:

• Degree in Computer Science, Engineering, AI, Math, Physics, or similar – or equivalent additional work experience
• Work experience deploying LLM/ML models to production
• Excellent problem solving skills and strong product mindset
• Excellent communication skills to interact with founding team and customers
• Ability to understand and implement technical state-of-the-art research papers
• Proficiency to write production-level code for AI/LLM based applications
• Proficiency with advanced Python workflows including Pytorch, Langchain, LlamaIndex, OpenAI or similar LLMOps libraries (Scikit-learn, pandas etc.)
• Experience with RAG and fine-tuning LLMs
• Nice to have
  • Working knowledge of Django and GCP
  • Early stage (series A or earlier) startup experience
  • Experience developing open source software
  • Excellent knowledge of authentication schemes