Recommender Systems Engineer (Market Signals)

Deeter Analytics

At Deeter Analytics, we’re building something that doesn’t get built twice in a generation.

Our goal is to create a fundamental trading model as capable as today’s most advanced AI systems — but applied to global markets. Not incremental signals or isolated strategies, but a system that can continuously interpret, learn from, and act on the evolving state of the world.

We train on a range of petabyte-scale and real-time alternative-data sources — capturing how narratives form, how sentiment propagates, and how collective behavior drives markets. This requires operating at the frontier of data infrastructure, model design, and compute, all tightly integrated into a single system.

You’ll work alongside a small group of elite engineers, AI researchers, and traders, in an environment defined by speed and ownership. We run experiments continuously. Ideas move from concept to production in hours. And the feedback loop is immediate — measured directly in live performance.

About the role

You will design systems that extract sentiment, narrative dynamics, and collective behavior signals from real-time social data, and convert them into representations that inform trading decisions.

This is not a standard recommender problem. The challenge is to extract meaningful signal from imperfect, fast-moving data, and make it useful under real-world constraints.

We prefer systems that improve with scale over systems that rely on manual tuning.

What you’ll work on

● Ranking and structuring large volumes of real-time social data

● Modeling:

○ sentiment and emotional intensity

○ narrative shifts

○ collective dynamics across users and time

● Building representations of how information propagates and amplifies

● Adapting recommender systems and embedding methods to financial signal generation

● Improving signal quality under distribution shift and imperfect data

What we’re looking for

We’re looking for people who can reason from first principles about what should be modeled, why it matters, and how to improve it with scale.

Strong signals:

● You have built or shaped ranking, recommendation, or signal systems where quality mattered

● You have a strong track record of improving systems beyond baseline performance

● You think naturally in terms of signal vs. noise, feedback loops, and temporal dynamics

● You move quickly, test ideas, and iterate without waiting

Bonus signals:

● Experience with systems where ranking quality directly impacted outcomes

● Experience working on problems involving information propagation, sentiment, or collective behavior at scale

● Strong intuition for real signal vs. overfitting