Concision is building a modern spreadsheet and workflow platform. As an ML/AI Researcher at Concision, you’ll be responsible for building state-of-the-art document processing and ai agents infrastructure.

Our AI-native spreadsheet allows users to automate manual research, process thousands of documents in minutes, and extract valuable insights from the web, all within a simple and intuitive interface.

Why You Should Consider Joining

• Build Production-Grade AI: This isn't a research role. You will ship real-world AI solutions that are used in mission-critical flows by global companies from day one. Your work will have immediate and measurable impact.

• Solve Unique Engineering Challenges: We are tackling novel problems at the intersection of LLMs, asynchronous job processing, and large-scale data extraction. You'll be working on building reliable, low-latency AI systems that can handle a massive variety of unstructured data.

• A New Category of Software: We're building the next-generation AI platform. The market for automating research and document processing has expanded 1000x due to LLMs, and you'll be on the front lines, engineering the core of this new technology.

• Outsized Impact: We're punching well above our weight, supporting significant customer and revenue metrics with a lean team. As a foundational engineer, you will have immense influence over our technical direction and the DNA of our engineering culture.

• Talent-Dense Team: You’ll join a high-performance team that operates with speed and autonomy. We are deeply technical and passionate about building robust, scalable systems.

• Strong Backing: We are backed by private investors who believe in our long-term vision and our engineering-first approach.

We're a lean team, and our customer base is growing too fast for us to keep up. We're looking for talented engineers to join our founding team ahead of our next round and execute on an ambitious technical roadmap.

Impact

You are building the engine of the Concision platform. Your work will directly define the capabilities, speed, and reliability of our core product.

• Build the AI Agent Infrastructure: You will design and implement the systems that allow thousands of AI agents (cells) to run in parallel, from web scraping and data enrichment to complex, multi-step reasoning.

• Scale Document Intelligence: You will enhance our document processing pipeline to handle hundreds of thousands of PDFs, extracting structured data with high accuracy and building systems that can understand complex layouts and formats.

• Optimize for Performance & Cost: You will be obsessed with the efficiency of our AI stack, optimizing everything from prompt engineering and model selection to data chunking strategies to deliver fast, accurate results while managing costs.

• Create Self-Correcting Systems: You will work on building data flywheels and evaluation pipelines that allow our models and systems to learn from user interactions and automatically improve over time.

Role

• Design, build, and maintain the production machine learning systems that power our intelligent columns and workflow automation blocks.

• Develop robust data pipelines for ingesting, processing, and enriching data from diverse sources like websites, PDFs, and third-party APIs.

• Fine-tune and deploy both open-source LLMs to solve specific customer problems in data extraction and generation.

• Own the MLOps lifecycle: build monitoring, evaluation, and CI/CD for our AI systems to ensure high availability and performance.

• Collaborate directly with the CEO and CTO to translate customer needs into technical specifications and production-ready features.

• Stay on the cutting edge of AI research and apply the latest practical techniques to continuously improve our platform's capabilities.

• All AI Tools covered - we embrace the new way of working and give you access to all the latest SOTA tools: Cursor Pro, Codex, and Gemini Pro.