At JetBrains, code is our passion. Ever since we started, back in 2000, we have strived to make the strongest, most effective developer tools on earth.
We believe that the data domain will soon undergo the same kind of disruption that is currently happening in software engineering. AI agents will become increasingly capable of solving tasks related to analytics, working with company data, and data engineering.
JetBrains is building the next generation of intelligent tooling for the global software and data ecosystem. Our mission is to create the infrastructure that automates the discovery, structuring, and evaluation of rich, organization-specific context, enabling AI agents to operate reliably within complex company environments.
We are seeking an ML Solutions Architect to work alongside experienced engineers, researchers, and product leaders at the intersection of AI, developer tools, and large-scale systems. If you’re passionate about democratizing data and transforming how businesses operate in the new era of agents, we want you on our team!
Your responsibilities will include:
- Designing and implementing ML- and LLM-based solutions for automated context discovery, enrichment, and evaluation.
- Architecting systems that connect internal data, metrics, documents, and tools into robust contextual foundations for agents.
- Providing technical expertise in prompt engineering, RAG architectures, model selection, and inference optimization.
- Defining and maintaining metrics and benchmarks for context quality, relevance, and downstream task success.
- Collaborating with product and engineering teams to identify customer feedback and shape the platform roadmap.
- Mentoring ML engineers and researchers, driving best practices in experimentation, architecture, and evaluation.
We expect you to have:
- At least five years of experience in ML/AI systems, with at least two years focused on LLMs and generative AI.
- A deep understanding of the LLM ecosystem, including model architectures and fine-tuning approaches.
- Hands-on experience with:
- Prompt engineering and LLM pipeline design, including evaluation.
- Agentic frameworks such as LangChain, LlamaIndex, LangSmith, smolagents, or an equivalent.
- Vector databases and retrieval-augmented generation (RAG) patterns.
- Deploying and scaling LLM-powered applications using APIs (e.g. OpenAI or Anthropic) or open-source models.
- Strong Python skills.
- Excellent communication skills, with the ability to explain complex technical concepts to diverse audiences.
- Proficiency in English, both written and verbal.
It will be an added bonus if you have:
- Worked with company-internal data, metrics, or BI tools.
- Maintained and supported Python open-source projects (e.g. handling community issues, reviews, releases, and long-term stability for external users).
- Evaluated LLM output quality in real-world applications.
- Worked with information retrieval or knowledge engineering.
- Worked with reinforcement learning for agents and/or multi-agent systems, especially in production or complex simulated environments.
#LI-KP1
We process the data provided in your job application in accordance with the Recruitment Privacy Policy.
