Software Engineer

Hyper Lychee Labs; India; Teletrabalho; INR 3 246 000 - 7 790 000; Tempo parcial

Resumo da oferta

Hyper Lychee Labs is seeking an expert contractor to design reinforcement learning environments that test a model’s ability to solve real software engineering problems: track down subtle bugs, implement non-trivial features, refactor, and optimize performance.

You will define the problem, build reproducible environments, and write deterministic verifiers plus a reference solution, ensuring tasks are unambiguous and verifiable across diverse implementations.

Qualificações

• Hands-on expertise in at least one programming language (Python, Java, Rust, Go, C++, or TypeScript).
• Deep understanding of algorithms, data structures, and software engineering principles.
• Proven ability to debug complex systems, resolve bugs, and deliver effective optimizations.

Responsabilidades

• Create realistic, challenging coding tasks for frontier AI models, drawn from repositories you know well.
• Design problems that require real engineering skill — subtle bugs, non-trivial features, meaningful performance work.
• Build a reproducible environment for each task.
• Write deterministic verifiers that accept correct solutions across different valid implementations.
• Provide a reference solution showing how the task can be solved.
• Flag tasks that turn out to be ambiguous or unverifiable rather than submitting them.

Conhecimentos

Python

Java

Rust

Go

C++

TypeScript

Descrição da oferta de emprego

You’ll need:

Hands-on expertise in at least one of Python, Java, Rust, Go, C++, or TypeScript

Your tasks:

Build challenging coding problems from real repositories, with reproducible environments and verifiers

Role Type

Contractor (~15 hrs a week)

Location:

Remote

Job Description

You’ll create Reinforcement Learning Environments that test a model’s ability to solve real software engineering problems: tracking down subtle bugs, building non-trivial features, refactoring, and optimizing performance. Each task means defining the problem, building a reproducible environment, and writing a reference solution.

Scope of Work

• Create realistic, challenging coding tasks for frontier AI models, drawn from repositories you know well.
• Design problems that require real engineering skill — subtle bugs, non-trivial features, meaningful performance work — not lookup or boilerplate.
• Build a reproducible environment for each task.
• Write deterministic verifiers that accept correct solutions across different valid implementations, while rejecting incorrect, incomplete, or hard-coded approaches.
• Provide a reference solution showing how the task can be solved.
• Flag tasks that turn out to be ambiguous or unverifiable rather than submitting them.

Preferred Qualifications

• Significant hands-on expertise in at least one of: Python3, Java, Rust, Go, C++, or TypeScript.
• Deep understanding of algorithms, data structures, and software engineering principles.
• Proven ability to debug complex systems, resolve bugs, and deliver effective optimizations.
• Experience with large codebase refactoring and legacy system modernization.
• Track record of delivering high-impact features from conception through delivery.
• Strong documentation and communication skills to articulate technical concepts clearly.
• Interest in AI and its technical challenges — previous AI experience not required.

Compensation Structure

Compensation is output-based; experts are paid per task that meets the project specifications. The time required may vary depending on your experience and workflow.

Start Timeline & Availability

We typically fill roles within 48 hours and are looking for experts ready to jump in right away. If selected, we expect you to start your first tasks within 24–48 hours of completing onboarding.