Senior Software Engineer — Agentic Coding

Alignerr Corp.; São Paulo; Teletrabalho; BRL 482 000 - 827 000; Tempo parcial

Resumo da oferta

Alignerr is seeking a Senior Software Engineer to lead the development of agentic coding systems that autonomously plan, write, test, and iterate on production code. This fully remote, flexible hourly contract role offers 10–40 hours per week and invites engineers to shape next-gen AI tooling from São Paulo or anywhere.

You will evaluate AI-generated code for correctness and efficiency, contribute to benchmarking, and collaborate with researchers and engineers working on large language models

Qualificações

• 5+ years of professional software engineering experience.
• Proficient in one or more major languages: Python, JavaScript/TypeScript, Java, C++, Go, or Rust.
• Strong understanding of software architecture, design patterns, and system design.

Responsabilidades

• Design, build, and refine agentic coding workflows where AI autonomously plans, writes, tests, and iterates on code.
• Evaluate AI-generated code for correctness, efficiency, security, and best practices.
• Create complex coding challenges and benchmarks to stress-test agentic AI capabilities.
• Provide expert feedback on AI reasoning, tool usage, and code quality.
• Identify failure modes and edge cases where autonomous agents break down.
• Develop evaluation frameworks, rubrics, and testing harnesses for agentic systems.
• Collaborate asynchronously with researchers and engineers on large language models and AI agents.
• Work independently on task-based assignments at your own pace and schedule.

Conhecimentos

5+ years exp

Languages: Python/JS/Java/C++/Go/Rust

Software architecture

CI/CD

Code review

Ferramentas

LangChain

OpenAI tooling

Descrição da oferta de emprego

Senior Software Engineer — Agentic Coding (AI Training)

About The Role

What if your software engineering expertise could define how the next generation of AI writes, debugs, and ships code on its own? We're looking for Senior Software Engineers in São Paulo to work at the frontier of agentic AI — building, evaluating, and improving autonomous coding systems that can reason through complex problems, execute multi-step plans, and produce production-quality software with minimal human intervention.

São Paulo is Latin America's largest tech hub, and we're looking for senior engineers here who are ready to apply their deep skills to the most transformative technology of our time. Your code, judgment, and architectural thinking will directly shape how these systems evolve.

This is a fully remote, flexible contract role. If you're a senior engineer who's excited about agentic AI and wants to work on problems that genuinely matter, we want to hear from you.

• Organization: Alignerr
• Type: Hourly Contract
• Location: Remote
• Commitment: 10–40 hours/week

What You'll Do

• Design, build, and refine agentic coding workflows — systems where AI autonomously plans, writes, tests, and iterates on code
• Evaluate AI-generated code for correctness, efficiency, security, and adherence to best practices
• Create complex, real-world coding challenges and benchmarks to stress-test agentic AI capabilities
• Provide expert-level feedback on AI reasoning chains, tool usage, and code output quality
• Identify failure modes, edge cases, and areas where autonomous agents break down
• Develop and improve evaluation frameworks, rubrics, and testing harnesses for agentic systems
• Collaborate asynchronously with researchers and engineers working on large language models and AI agents
• Work independently on task-based assignments at your own pace and on your own schedule

Who You Are

• 5+ years of professional software engineering experience — you've built, shipped, and maintained real systems
• Proficient in one or more major languages: Python, JavaScript/TypeScript, Java, C++, Go, or Rust
• Strong understanding of software architecture, design patterns, and system design principles
• Comfortable reading, reviewing, and debugging code you didn't write — across diverse codebases and styles
• Deep familiarity with modern development workflows: version control, CI/CD, testing frameworks, and code review
• Excellent problem-solving and analytical thinking — you can reason through ambiguous, multi-step technical challenges
• Clear, precise technical communicator who can articulate why code is good, bad, or broken
• Self-directed and reliable when working independently without close supervision
• Genuinely curious about AI, LLMs, and the future of autonomous software development
• Strong written communication skills in English

Nice to Have

• Experience with AI/ML systems, prompt engineering, or LLM-based tooling
• Familiarity with agentic frameworks (e.g., LangChain, AutoGPT, CrewAI, OpenAI function calling)
• Background in developer tools, compilers, static analysis, or code generation
• Experience evaluating or training AI models — RLHF, preference labeling, or similar workflows
• Contributions to open-source projects or a strong public engineering portfolio
• Knowledge of multiple programming paradigms and languages

Why Join Us

• Work at the absolute frontier of agentic AI — one of the most exciting areas in technology today
• Collaborate on cutting‑edge projects alongside leading AI research labs
• Fully remote and flexible — work when and where it suits you
• Freelance autonomy with the depth and challenge of meaningful, high‑impact engineering work
• Your expertise directly shapes how AI agents write software — influencing tools used by millions of developers
• Ongoing learning exposure to state‑of‑the‑art large language models and autonomous systems
• Potential for long‑term engagement and contract extension as projects scale