Founding ML Engineer

Founding ML Engineer – Spectrum at JetBrains

Join Spectrum, a JetBrains startup incubator project, as a Founding ML Engineer to build the AI and ML engineering stack for a revolutionary semantic layer platform. Spectrum aims to create a unified knowledge repository from an organization's code, documentation, and issues, serving as a single source of truth for product and architectural knowledge that AI agents can efficiently search and reason over.

Key Responsibilities:

• Design and build end-to-end ML/LLM solutions for data ingestion, knowledge extraction, retrieval, and reasoning

• Create datasets, metrics, and pipelines that drive measurable system improvements

• Architect and optimize agents for context retrieval, knowledge extraction, and data alignment through prompt engineering, model selection, and inference optimization

• Establish MLOps practices including orchestration, observability, and experiment tracking

• Collaborate with engineering teams on system architecture and with JetBrains Research on the research agenda

• Define hiring criteria and grow the ML team while shaping team culture

Required Experience:

• Proven ML/AI leadership track record with 5+ years in ML/AI systems

• At least 2 years focused on LLMs and generative AI

• Deep expertise in prompt engineering, LLM pipeline design, and evaluation

• Hands-on experience with agentic frameworks (LangChain, LlamaIndex, LangSmith, smolagents or equivalents)

• Proficiency with vector databases and RAG patterns

• Experience deploying and scaling LLM applications using commercial or open-source models

• Strong Python skills; Kotlin knowledge is a bonus

• Fluent English communication abilities

Ideal candidates bring experience with knowledge graphs, ontologies, early-stage startups, code analysis tools, multi-agent systems, and contributions to relevant open-source projects.