AI/ML Engineer

• Type: Full-time (part-time considered)
• Experience Level: Senior to Staff (early career considered)
• Compensation: Negotiable, includes equity and benefits

Hi there —

We're Lab24, and we're building a context-aware project management agent that helps teams actually get work done. Our goal is to push beyond chatbots and prompt wrappers—we want to build something that thinks with you, not just for you.

If you're passionate about large language models, intelligent retrieval, and architecting fast, reliable AI systems, this is your chance to help define how AI truly integrates into day-to-day work.

What we're looking for

We're looking for an engineer who understands that building useful AI starts with managing the right context. You know that retrieval isn't just a pipeline—it's the foundation of intelligence. You're equally focused on the quality of information fed into the model and the latency with which it responds.

You'll be one of our first ML hires, and help us design the full intelligence and data layer—from embedding strategies to data infrastructure, query planning, and memory.

Things you should be good at

• Building LLM-powered applications using OpenAI, Anthropic, or open-source models
• Designing and implementing RAG (Retrieval-Augmented Generation) systems for structured and unstructured data
• Deep understanding of data retrieval pipelines, including working with data lakes, object stores, and unstructured document ingestion
• Comfortable designing data normalization, indexing, and query strategies at scale
• Strong grasp of vector databases (Pinecone, Qdrant, Weaviate, or in-house solutions)
• Experience working with Python, ideally some exposure to TypeScript or willingness to collaborate with TS-based systems
• A thoughtful approach to latency optimization: reducing absolute model and I/O latency and optimizing perceived UX responsiveness (e.g. progressive responses, streaming)
• Familiarity with frameworks like LangChain, LlamaIndex, or custom-built pipelines

Bonus experience

• Knowledge of embedding tuning, reranking models, or hybrid search techniques
• Experience working with data lake infrastructure (e.g., S3, GCS, Delta Lake, etc.) in production
• Experience designing real-time pipelines with caching layers, background updates, or on-demand fetching
• Interest in memory systems, agents, or long-context LLM architectures
• Familiarity with semantic graphs, relationship modeling, or ontologies
• Previous experience shipping ML features inside a product, not just research

What we don't care about

We don't care if you have a PhD, master's, or no degree at all. We care that you've built real things, understand tradeoffs, and care about pushing the boundary of what's possible.

How to apply

Please include:

• Your résumé
• A portfolio — this could be GitHub, a blog post, a demo, or anything that gives us a feel for how you think and what you've built

If you're excited about building real-world, low-latency, context-rich AI products—we'd love to talk. You'll have a seat at the table from the start and help us architect the core intelligence layer for how teams get work done.