Software Engineer, Platform (India)

Ovii's Interpretation of the Role

We need a Software Engineer to design and operate a low‑latency, scalable inference stack for cutting‑edge foundation models. You will partner with research and product teams, build high‑performance data pipelines, and own end‑to‑end platform reliability.

Role Snapshot

• Build low‑latency model inference stack
• Develop large‑scale distributed systems
• Create high‑throughput data pipelines
• Collaborate with research and product engineers
• Write clean Go, Python, and Next.js code
• Drive observability and performance
• Operate with high autonomy

Must-Have Requirements

• Go
• Python
• Next.js
• Distributed systems
• Low‑latency serving
• Observability
• software engineering
• product engineering
• ML platform engineering
• large‑scale distributed systems

Nice-to-Have Signals

• Machine learning and generative model background
• Navigating complex monorepos
• machine learning
• generative models

Work Setup

• Location: Bangalore, India
• Work mode: REMOTE
• Remote scope: UNSPECIFIED
• Remote countries: India, Bangalore
• Employment type: Full-Time

Eligibility Gates

• Visa sponsorship: yes

Not Specified in JD

• Salary range
• Visa guarantee
• Remote eligibility specifics
• Education requirement
• Certifications

What You'll Likely Work On

• Design and implement a low‑latency, scalable model inference and serving layer for SSM foundation models
• Build highly parallel data processing and evaluation pipelines for model training
• Engineer large‑scale distributed services with strong performance, reliability, and observability guarantees
• Partner with research scientists to translate novel algorithms into production‑ready features
• Maintain a monorepo codebase, ensuring code quality and clean architecture across backend and frontend
• Own end‑to‑end platform reliability, monitoring, and incident response

Good Fit If You Have

• Passion for AI/ML and generative model research
• Enjoys solving ambiguous, high‑impact problems
• Thrives in fast‑moving, high‑quality delivery environments