Pranav Marla

AI Engineer / Builder

I build AI products that can scale to millions of users.

I currently work as an AI Engineering Consultant at DAZN, a globally leading sports streaming platform. My work is focussed on working on AI pipelines that are highly scalable and robust.

I'm also building a visual reasoning agent that can reason about images and videos using hierarchical reasoning called Kalpa.

I also love making music and birdwatching.

ChatGPT logo
Claude logo
DeepSeek logo
Hugging Face logo
Pranav Marla portrait
Pranav Marla portrait detail
Pranav Marla portrait detail
Pranav Marla portrait detail

Work Experience

DAZN logo
DAZN
AI Engineering Consultant

Building AI systems with a strong bias toward reliability, product usefulness, and structured execution.

  • Designed agent workflows for multi-step reasoning tasks where orchestration quality mattered as much as raw model quality.
  • Worked on evaluation patterns that helped separate fluent output from genuinely useful reasoning.
  • Focused on turning experimental agent behavior into interfaces and flows that felt production-oriented rather than purely research-driven.
  • Explored planning systems that break large tasks into smaller units with clearer failure boundaries.
  • Collaborated across product and engineering constraints to keep AI features grounded in actual user value.
Feuji logo
Feuji
Software Engineer

Applied Engineering work that pushed me deeper into practical AI implementation and system design.

  • Built and shipped software in environments where technical decisions had to balance speed, clarity, and maintainability.
  • Developed a stronger instinct for production tradeoffs instead of treating engineering as purely theoretical optimization.
  • Worked across ambiguous requirements and learned how to define structure when the problem itself was not fully clean yet.
  • Sharpened my interest in how intelligence systems behave under messy real-world constraints.
  • Used that experience as a foundation for moving further into agent design and reasoning-centric AI work.
Previous company logo
Previous Company
Role title

Placeholder slot for the company before Feuji.

  • Add the company name, role, dates, and location here.
  • Replace this placeholder summary with the actual work description.
  • Add 4-5 concise bullets about impact, systems, or scope.

Education

Northeastern University logo
Northeastern University
M.S. in Computer Science

Academic grounding, but more importantly, a period that shaped the questions I still care about.

  • Built the technical base that later made applied AI work easier to approach with confidence.
  • Spent time thinking beyond implementation and into epistemology, truth, and what reliable reasoning should mean in practice.
  • Developed an early fascination with systems that can support decision-making rather than merely generate text.
  • Started connecting software, philosophy, and intelligence as one coherent design space.
  • Carried those ideas directly into later work on recursive agents and structured evaluation.
Bachelor's institution logo
Bachelor's Institution
Bachelor's degree title

Placeholder slot for your bachelor's degree.

  • Add the university name and exact degree title here.
  • Use this slot for any emphasis you want to place on focus areas or notable work.
School logo
School
School qualification

Placeholder slot for school details.

  • Add the school name and qualification here.
  • Keep this concise unless you want to highlight something specific.

Projects

1. Kalpa kalpa.chat

A general LLM agent designed around Socratic reasoning, recursive task decomposition, transparent execution, and self-healing behavior.

The central idea is that complex tasks should not be handled as one-shot completions. They should be unpacked, inspected, challenged, and refined while the user can still see what is happening.

2. Debate Tree GitHub logo marlaman/DebateTree

A framework to steelman, structure, and visualize debates so reasoning quality becomes inspectable instead of rhetorical.

It came from a simple frustration: most arguments optimize for winning rather than for understanding. Debate Tree was an attempt to make disagreement legible.

3. treesofARC GitHub logo marlaman/treesofARC

A recursive-agent approach to the ARC Challenge with an emphasis on visualized reasoning and interpretable decomposition.

The project explored how recursive structure could help models treat hard symbolic tasks more like a solvable process than a blind guess.

Side Quests

Pranav DJing
SoundCloud soundcloud.com/pranav-marla Tracks / mixes
Curated playlist Set link later
Outside work
Music Ongoing

I make music with the same instinct I build systems with. I like structure, tension, rhythm, and release.

It is one of the few places where I can think in texture instead of specification, but the underlying obsession is still composition, clarity, and emotional precision.

Great blue heron in flight
Birdwatching
Secretary bird
Outside work
Birdwatching Ongoing

Birdwatching keeps me observational. It slows my attention down and rewards patience more than speed. The great blue heron was my spark bird — the one that made me start paying attention.

I like that it feels like pattern recognition without dashboards, memory without databases, and curiosity without immediate utility.

Ask AI

Ask anything about my work at DAZN, the ideas behind Kalpa, how I think about agents, or what I care about outside work.