Machine Learning Engineer (LLM, Search & Retrieval)

Inventive is building an AI-powered knowledge management platform for B2B sales teams. Our current focus is to automate parts of sales bidding (RFPs) and security review (questionnaires) workflows using the existing knowledge bases in enterprises.

We recently graduated from YCombinator and have raised a seed round from Valley's top investors. Our founding team comprises a repeat founder with a successful exit (post series-B), and product & research leaders from Google AI and Stanford.

Key elements of this role

We are looking for a research software engineer to join our team to help build systems with LLMs. You will be among the earliest hires at Inventive and will:

• Play a pivotal role in architecting & building the foundational tech platforms for the company.
• Be part of a team building a 0 → 1 product and have a significant influence & impact on the company's roadmap.
• Work in a fast-paced, entrepreneurial environment, alongside successful founders and some of the sharpest minds in AI and enterprise tech.

Specific role and responsibilities

• Build and improve robust and reliable search and retrieval systems built on top of large volumes of enterprise data.
• Build and optimize evaluation pipelines to drive reliability and accuracy in our systems.
• Architect and build key pieces of the back-end platform directly or indirectly related to the LLM systems.
• Work closely with the founding team to understand the client use cases and devise creative solutions which could be a combination of tech, UX, and HITL workflows.
• Invent solutions to improve system reliability, user experience, and robustness of LLM systems.

Requirements for this role

• Track record of working with deep learning systems and language models.
• Experience with information processing systems (search and retrieval systems are a plus).
• Competence in working with various technical components (including web backend, Docker, and cloud platforms).
• Eager to lead projects and capable of autonomous work.
• Proficiency in Python, Django and Docker.
• 3+ years of industry experience.
• Based in the SF Bay Area (or willing to move) in a reasonable time frame.