Your responsibilities, Design and implement RL environments that support large-scale agent evaluation and reinforcement learning experiments., Build task generation pipelines, dynamic datasets, and scripted environments with controlled complexity and stochasticity., Develop verifiers and reward models to automatically score trajectories and evaluate model reasoning., Collaborate with infrastructure and systems engineers to ensure environments are scalable, reproducible, and instrumented for detailed telemetry., Design APIs and orchestration frameworks for running, resetting, and evaluating agents across environments., Optimize environment performance, logging, and reward reproducibility across distributed setups.

5+ years of experience in Python software engineering., Minimum 3 years in a Data Scientist, Machine Learning/Environment Engineering position., Being able to work 2 p.m. - 10 p.m., Practical knowledge of AI frameworks (Langchain, Langraph, mcp-server )., Extensive practical experience in working with AI, including prompt engineering and vibe coding.

Optional, Knowledge of Codex or Claude Code., Experience in integrating AI with a system would be an advantage., Understanding of RL concepts - reward modeling, environment dynamics, verifiability, evaluation, and agent interaction loops., Familiarity with instrumentation, metrics, and data pipelines for RL evaluation., Expertise in planning your own work.

This is how we work, at the client's site, you focus on a single project at a time, you can change the project, you focus on product development, agile

Benefits, sharing the costs of sports activities, private medical care, remote work opportunities, flexible working time, integration events, extra social benefits, baby layette, school layette, employee referral program, charity initiatives, Gift vouchers for kids (birthdays, Christmas, Child's Day)

Recruitment stages, HR call (max 15 min.), Technical skills assessment via discussion of a case study, Technical interview with our client (max 30 min.)*

ACAISOFT POLAND Sp. z o.o., At Acaisoft we specialize in cloud-native application development and transformations from legacy to cloud-native environments., , We provide end-to-end software solutions, from business analysis, through project evaluation, to UI/UX, Frontend, and Backend design and implementation. We integrate manual and automated QA finest practices, to make sure that the final product is top-notch., , Our customers range from startups to large enterprises based in the US, mainly Silicon Valley, and Western Europe., , Since technology is constantly being developed at such a fast pace, we always strive to be one step ahead of the market and keep up with the latest solutions.

This is how we work,

About the project

You will be cooperating with a leading provider of AI evaluation and optimization solutions, trusted by multinational companies to optimize AI agents and detect performance issues in large language models.

In this role, you’ll help develop advanced reinforcement learning (RL) environments and scalable evaluation systems that guide and shape the behavior of cutting-edge AI models. The company’s mission is to enable safe, verifiable, and aligned AGI through rigorous, real-world agent evaluation.

Due to the client’s time zone, we would appreciate a candidate who can work 2 p.m. - 10 p.m.

Join us and make a real impact!

If you’re ready to broaden your horizons and work with an innovative company at the forefront of AI, we’d love to hear from you. You’ll help build the environments that shape how future AI systems are trained, evaluated, and aligned - and collaborate with world-class engineers and researchers on one of the most important technical challenges of our time.

About the project

You will be cooperating with a leading provider of AI evaluation and optimization solutions, trusted by multinational companies to optimize AI agents and detect performance issues in large language models.

In this role, you’ll help develop advanced reinforcement learning (RL) environments and scalable evaluation systems that guide and shape the behavior of cutting-edge AI models. The company’s mission is to enable safe, verifiable, and aligned AGI through rigorous, real-world agent evaluation.

Due to the client’s time zone, we would appreciate a candidate who can work 2 p.m. - 10 p.m.

Join us and make a real impact!

If you’re ready to broaden your horizons and work with an innovative company at the forefront of AI, we’d love to hear from you. You’ll help build the environments that shape how future AI systems are trained, evaluated, and aligned - and collaborate with world-class engineers and researchers on one of the most important technical challenges of our time.

Your responsibilities

• Design and implement RL environments that support large-scale agent evaluation and reinforcement learning experiments.
• Build task generation pipelines, dynamic datasets, and scripted environments with controlled complexity and stochasticity.
• Develop verifiers and reward models to automatically score trajectories and evaluate model reasoning.
• Collaborate with infrastructure and systems engineers to ensure environments are scalable, reproducible, and instrumented for detailed telemetry.
• Design APIs and orchestration frameworks for running, resetting, and evaluating agents across environments.
• Optimize environment performance, logging, and reward reproducibility across distributed setups.

Recruitment stages

• HR call (max 15 min.)
• Technical skills assessment via discussion of a case study
• Technical interview with our client (max 30 min.)*

Recruitment stages, HR call (max 15 min.), Technical skills assessment via discussion of a case study, Technical interview with our client (max 30 min.)*

ACAISOFT POLAND Sp. z o.o., At Acaisoft we specialize in cloud-native application development and transformations from legacy to cloud-native environments., , We provide end-to-end software solutions, from business analysis, through project evaluation, to UI/UX, Frontend, and Backend design and implementation. We integrate manual and automated QA finest practices, to make sure that the final product is top-notch., , Our customers range from startups to large enterprises based in the US, mainly Silicon Valley, and Western Europe., , Since technology is constantly being developed at such a fast pace, we always strive to be one step ahead of the market and keep up with the latest solutions.

This is how we work,

About the project

You will be cooperating with a leading provider of AI evaluation and optimization solutions, trusted by multinational companies to optimize AI agents and detect performance issues in large language models.

In this role, you’ll help develop advanced reinforcement learning (RL) environments and scalable evaluation systems that guide and shape the behavior of cutting-edge AI models. The company’s mission is to enable safe, verifiable, and aligned AGI through rigorous, real-world agent evaluation.

Due to the client’s time zone, we would appreciate a candidate who can work 2 p.m. - 10 p.m.

Join us and make a real impact!

If you’re ready to broaden your horizons and work with an innovative company at the forefront of AI, we’d love to hear from you. You’ll help build the environments that shape how future AI systems are trained, evaluated, and aligned - and collaborate with world-class engineers and researchers on one of the most important technical challenges of our time.