Junior Software Engineer

Simplify; San Francisco (CA); On-site; USD 255,000 - 345,000; Full time

Job summary

Simplify in San Francisco is hiring a junior software engineer to design and build reinforcement-learning environments for software engineering tasks. You will own the full lifecycle from concept to evaluation against frontier models, using Python and Docker/Linux tools in real engineering-like settings.

You will work on end-to-end problems in a small, fast-moving team, applying strong fundamentals to AI model behavior, and you will be in-person in SF, with opportunities to shape how frontier AI

Qualifications

• Experience with the latest AI tools and models.
• Strong problem-solving ability with intuition for AI model behavior.
• Able to work independently.
• In person in San Francisco.

Responsibilities

• Design and build reinforcement‑learning tasks and environments for software‑engineering challenges.
• Own the full lifecycle: from task concept through evaluation against frontier models.
• Evaluate coding‑agent outputs and identify subtle failure patterns.
• Build Python‑based systems, harnesses, and tooling around model training and evals.
• Work with Docker/Linux environments that mirror real engineering work.
• Own problems end‑to‑end in a small, fast‑moving team.

Skills

AI tools experience

Independent work

Strong problem-solving

Tools

Python

Docker

Linux

Job description

We're partnering with a top AI training lab in San Francisco to hire a junior software engineer — and they pay like it's a senior role: $300K base + equity + bonus, for new grads.

About the company

One-liner: Building high-fidelity RL environments used to train frontier AI models on real software‑engineering work.

Stage: 11–50 people, HQ in SF. They work directly with the top AI labs — their environments are used to train state‑of‑the‑art models.

Today, AI models learn coding from static datasets and toy problems. This team builds the realistic, simulated engineering environments — long‑horizon tasks, real tooling, real failure modes — that frontier labs use to train and evaluate the next generation of coding agents.

What you'll work on

• Design and build reinforcement‑learning tasks and environments for software‑engineering challenges
• Own the full lifecycle: from task concept through evaluation against frontier models
• Evaluate coding‑agent outputs and identify subtle failure patterns
• Build Python‑based systems, harnesses, and tooling around model training and evals
• Work with Docker/Linux environments that mirror real engineering work
• Own problems end‑to‑end in a small, fast‑moving team

Must‑have

• Experience working with the latest AI tools and models
• Exceptional problem‑solving ability — strong technical fundamentals and intuition for AI model behavior
• Able to work independently
• In person in San Francisco

Nice to have

• ML or AI experience (e.g., you've trained your own models) — not required
• Strong math/CS background (competitions like USACO/ICPC/olympiads)
• Competed in quiz bowl, debate, robotics
• Impressive personal projects
• $300K base + equity + bonus — at the junior level
• Your work directly shapes how frontier AI models learn to do real engineering
• Small fast moving team, no bureaucracy — high ownership from day one
• Work at the frontier of RL, agents, and evaluation with the top AI labs as your customers