Founding Engineer - Vecflow

Why Vecflow?
The next few years will revolutionize how we interact with computers. It's not just chat; it's advanced retrieval, agents, and workflow automation. We're bringing it to lawyers because they deal with textual information daily and, frankly, they deserve better software. We are looking for exceptional candidates interested in working at an early startup.
As an early engineer at Vecflow, you will be instrumental in designing and building the core infrastructure that powers our product. You'll work closely with the founding team to develop scalable and robust backend solutions that align with our business goals. This role offers a unique opportunity to influence the company's direction and build a product from the ground up.
We are rethinking the way we interact with LLMs, not merely as chatbots, but as autonomous systems. You will be at the ground level of this change and help build the future.
Your Responsibilities

1. Architect, design, and implement the backend infrastructure, ensuring scalability, reliability, and security.
2. Agentic workflows: design and implement LLM agents that use these basic primitives and external tools to deliver high-quality, long-form work outputs.
3. Building production-quality LLM/RAG applications tailored to legal
4. Large-scale search and retrieval: Optimize search and retrieval protocols over large, heterogeneous databases and vectorstores.
5. Evaluation: Create rigorous evaluation protocols combining human preference judgments from domain experts and synthetic data generation.
6. Zero-to-one product development: rapidly prototype, evaluate, and integrate new product features and custom projects for our customers.
7. Develop and maintain APIs and services that power our front-end applications, ensuring seamless integration and performance.
8. Optimize the backend architecture for speed, efficiency, and scalability as the product and user base grow.

Required Skills

1. Expertise in scalable backend stack in Python and DB work in PostgreSQL and No-SQL
2. Experience using LLMs through model providers, libraries (langchain, llama-index, etc)
3. Experience with vector DBs, embeddings, and general NLP concepts
4. Experience with API design, development, and integration, including RESTful APIs.
5. Track record of shipping high-quality products
6. Experience with AI model deployment, including scaling, optimization, and performance tuning in a production environment.
7. Can translate open-ended problems into actionable, short-term goals and execute them aggressively.

Compensation and Benefits
In consideration of market analysis and relevant factors, the salary range for this position is USD $110,000 to $160,000 and includes stock options. However, adjustments outside this range may be considered for candidates whose qualifications significantly differ from those outlined in the job description. We also provide a relocation stipend for those moving to New York City.