About the Role
The AI for Code team at JetBrains is developing next-generation coding agents and agentic workflows. This role involves transforming internal and open-weight models into production-ready coding agents, focusing on model training, fine-tuning, context engineering, tool use, evaluation, feedback loops, and product integration. You will build systems used by tens of thousands of developers, impacting the future of AI in software development.
Responsibilities
- Build production-ready coding agents and agentic workflows for real developer tasks within JetBrains products.
- Transform model capabilities into dependable product behavior using prompt design, context construction, fine-tuning, and other post-training techniques.
- Design and enhance the agent loop, including tool use, execution strategy, safeguards, and task completion quality.
- Create evaluation suites and quality infrastructure for agent behavior, encompassing online/offline evaluations, regression checks, failure analysis, and release criteria.
- Develop feedback loops from real-world usage to improve data, evaluations, and agent behavior.
- Work with both hosted frontier APIs and self-hosted or open-weight models, making pragmatic decisions based on capability, latency, reliability, privacy, and cost.
- Collaborate with product managers, software engineers, ML engineers, and researchers for end-to-end feature shipping.
- Define the technical direction for future work, especially in ambiguous areas requiring strong judgment.
Requirements
- Strong software engineering fundamentals and a proven track record of shipping complex systems to production.
- Hands-on experience building LLM-powered products, coding agents, or other AI systems.
- Experience improving model behavior through systematic iteration (prompting, context engineering, fine-tuning, preference optimization, etc.).
- Practical experience with evaluation and benchmarking for LLM systems, including defining task-grounded success metrics and catching regressions.
- Experience working with noisy real-world signals, not just clean benchmark datasets.
- Good judgment regarding trade-offs between model quality, latency, reliability, privacy, and cost.
- Confidence in working with ambiguity and taking ownership of direction over multiple iterations.
- Strong communication skills to align engineering and product decisions.
Skills
- LLM-powered products
- Coding agents
- AI systems
- Prompting
- Context engineering
- Fine-tuning
- Preference optimization
- Post-training methods
- LLM system evaluation
- Benchmarking
- Success metrics definition
- Regression detection
- Real-world signal analysis
- Model quality assessment
- Latency optimization
- Reliability engineering
- Privacy considerations
- Cost management
- Ambiguity management
- Ownership
- Communication
Location
- Remote
- Office
Work Type
- Remote
- Hybrid
- Full-time
Experience Level
- Staff
- Senior
Salary/Compensations
- Strong base salary. Competitive pay that reflects your skills and experience.
Benefits
- Flexible work location
- Remote work (up to 30 days per year from abroad)
- Extra time off
- Medical insurance allowance
- Learning and development opportunities (conferences, courses, language classes)
- Relocation support
- Language classes
- Hot meal or lunch allowance on workdays
- Mental health support
- Sports benefit (on-site gym or sports club stipend)
- Internal events
About the Company
- At JetBrains, we build developer tools used by millions of engineers.
- We are building the next generation of coding agents and agentic workflows.
- We aim to create systems that understand codebases, plan and execute multi-step tasks, collaborate with developers, and ship reliable results inside real development environments.
Equal Opportunity
- We are an equal opportunity employer.
- We know great ideas can come from anyone, anywhere. That’s why we do our best to create an open and inclusive workplace – one that welcomes everyone regardless of their background, identity, religion, age, accessibility needs, or orientation.
- We process the data provided in your job application in accordance with the Recruitment Privacy Policy.
