Sign up to save your podcasts
Or
Share Denis Lukyanov: Quant Research, GenAI Agents, and Trading Systems | Blushing Quants #17
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Denis Lukyanov: Quant Research, GenAI Agents, and Trading Systems | Blushing Quants #17
Denis Lukyanov is a quantitative researcher and AI/ML practitioner working at the intersection of finance, machine learning, and agentic systems.
In this episode, we get into what it really takes to integrate agentic systems and large language models into quant workflows, and why the hard part is not generating ideas quickly, but building something structured, testable, and useful in practice.
We talk about the gap between quick AI prototypes and production-grade systems, why planning still matters more than coding speed, and how domain expertise remains the real bottleneck even as the tools improve. Denis breaks down how he thinks about combining traditional machine learning and deep learning with GenAI agents: LLMs can add real value as orchestrators, analysts, and research accelerators, but they still should not be trusted to make decisions. We also get into context windows, knowledge systems, guardrails, model-as-judge workflows, regime detection, quantitative research loops, and why serious trading systems still need explicit logic, strong data, and human control.
If you care about how AI is actually being used inside quant research today, what separates real systems from AI theater, and how to think clearly about agents, models, and market structure without losing rigor, don’t miss this one.
*DISCLAIMER*
The information shared on this podcast is for educational and informational purposes only and reflects the personal opinions of the hosts and guests at the time of recording. Nothing in this podcast constitutes financial, investment, legal, tax, or trading advice, and nothing should be interpreted as a recommendation to buy, sell, or hold any security, cryptocurrency, derivative, or financial product.
Trading and investing involve substantial risk, including the possible loss of all or part of your capital. You are solely responsible for your own decisions, and you should consult a qualified professional before making financial decisions. By listening to this podcast, you agree that the hosts, guests, and producers are not liable for any losses or damages arising from the use of any information discussed.
View all episodes
By theblushingquantsDenis Lukyanov is a quantitative researcher and AI/ML practitioner working at the intersection of finance, machine learning, and agentic systems.
In this episode, we get into what it really takes to integrate agentic systems and large language models into quant workflows, and why the hard part is not generating ideas quickly, but building something structured, testable, and useful in practice.
We talk about the gap between quick AI prototypes and production-grade systems, why planning still matters more than coding speed, and how domain expertise remains the real bottleneck even as the tools improve. Denis breaks down how he thinks about combining traditional machine learning and deep learning with GenAI agents: LLMs can add real value as orchestrators, analysts, and research accelerators, but they still should not be trusted to make decisions. We also get into context windows, knowledge systems, guardrails, model-as-judge workflows, regime detection, quantitative research loops, and why serious trading systems still need explicit logic, strong data, and human control.
If you care about how AI is actually being used inside quant research today, what separates real systems from AI theater, and how to think clearly about agents, models, and market structure without losing rigor, don’t miss this one.
*DISCLAIMER*
The information shared on this podcast is for educational and informational purposes only and reflects the personal opinions of the hosts and guests at the time of recording. Nothing in this podcast constitutes financial, investment, legal, tax, or trading advice, and nothing should be interpreted as a recommendation to buy, sell, or hold any security, cryptocurrency, derivative, or financial product.
Trading and investing involve substantial risk, including the possible loss of all or part of your capital. You are solely responsible for your own decisions, and you should consult a qualified professional before making financial decisions. By listening to this podcast, you agree that the hosts, guests, and producers are not liable for any losses or damages arising from the use of any information discussed.