Build the behavioral intelligence infrastructure powering the future of commerce

Company:

Markopolo AI Inc.

Experience:

3–5 years

Type:

Full-Time (40 hours/week)

Location:

Remote / Hybrid — Bangalore (India) or Dhaka (Bangladesh)

Hybrid Policy:

2 days in office, 3 days work from home

Reports To:

Engineering Lead

ABOUT THE ROLE

Markopolo AI (markopolo.ai) is building the behavioral intelligence layer for the internet. Our flagship model, ATHENA—a 709M-parameter behavioral foundation model—predicts what users will do 10–30 seconds before they act. Trained on 40M+ behavioral sequences across 603 independent businesses, ATHENA achieves 72.67% Top-1 accuracy on 116-class next-event prediction and runs at 0.01 ms inference latency via extreme compression (709M parameters → 50KB WebAssembly). We are the “Stripe for behavior”: foundational infrastructure powering real-time personalization, cart recovery, fraud detection, and the coming wave of agent-to-agent commerce. We are a small, intense team building something the world hasn’t seen before.

We’re venture-backed by HF0 (investors in Ramp, Pave, Fabric, Clerk), Joa Capital (Saudi Sovereign Fund’s arm), and are Headquartered in San Francisco, USA, with offices in Dhaka, Bangalore, and Riyadh.

As a Software Engineer II, you will own and ship core systems that directly power ATHENA’s prediction pipeline, edge deployment infrastructure, and enterprise integrations. You won’t just write features—you'll design systems that operate at sub-millisecond latency, handle millions of concurrent sessions, and compress state-of-the-art models into packages smaller than a JPEG. This role is for engineers who build things they’re proud of and want to work at the frontier of applied AI.

WHAT YOU'LL DO

• Design, build, and own production systems within ATHENA’s real-time behavioral prediction pipeline.
• Architect and implement streaming data infrastructure (Kafka/Redpanda, ClickHouse, gRPC) for ingesting and processing millions of behavioral events per second.
• Develop and optimize edge-deployment systems: WebAssembly modules, model compression pipelines, and client-side inference engines.
• Build robust API surfaces and webhook/streaming integrations for enterprise customers and partner platforms (Stripe, Vercel, Shopify, n8n).
• Collaborate with the ML team on model serving infrastructure, A/B testing frameworks, and continuous training pipelines (Modal, PyTorch, TensorFlow Lite).
• Lead code reviews, contribute to architectural decisions, and mentor junior engineers and interns.

REQUIREMENTS

• 3–5 years of professional software engineering experience with production systems at scale.
• Strong proficiency in: Python, TypeScript/Node.js.
• Deep experience with distributed systems, streaming architectures, or real-time data pipelines.
• Solid understanding of system design: message queues, caching, load balancing, and database modeling.
• Experience with cloud infrastructure (AWS, GCP, or Modal) and containerized deployments (Docker, Kubernetes).
• Familiarity with ML model serving, inference optimization, or edge computing is strongly preferred.
• Strong debugging skills and comfort operating production systems under pressure.

NICE TO HAVE

• Experience with WebAssembly, model quantization, or knowledge distillation.
• Background in behavioral analytics, session recording, or real-time personalization.
• Contributions to open-source projects or published technical writing.
• Experience building or integrating with payment infrastructure or commerce platforms.
• Familiarity with privacy-preserving architectures and client-side computation.

HOW TO APPLY—WHAT WE WANT TO SEE

We don’t believe in LeetCode marathons. We believe in seeing how you think and what you’ve built. Your application must include:

A System Architecture You’re Proud Of

Share a system architecture that you created or significantly contributed to. This can be:

• An architecture diagram (Miro, Excalidraw, Lucidchart, hand-drawn — we don’t care about polish, we care about thinking).
• A one-page Word/PDF description explaining the system: what problem it solved, the key design decisions you made, trade-offs you navigated, and what you’d change if you rebuilt it today.
• Bonus: include metrics or outcomes (latency, throughput, uptime, cost savings, etc.).

We want to understand how you decompose complex problems, make trade-offs under constraints, and communicate technical decisions. This is the single most important part of your application.

WHY MARKOPOLO

• Work on a 709M-parameter behavioral foundation model (ATHENA) that predicts human actions before they happen — real frontier AI, not wrapper products.
• Remote-first culture with hybrid flexibility (2 days in office, 3 days Work from home)
• Competitive compensation with equity options for full-time roles.
• Learn from a team pushing the boundaries of edge AI, model compression, and real-time behavioral intelligence.

Ready to build the future of behavioral intelligence?

Apply by sending your resume and the system architecture to:

careers@markopolo.ai