Founding ML Engineer – Build AI Knowledge Platform

About the role

We are looking for a top‑class ML Engineer to lead the AI and ML stack of Spectrum, an innovative knowledge‑graph platform backed by JetBrains' startup incubator. You will shape the research agenda, own the end‑to‑end LLM solution, and drive the creation of a living specification for software‑building organizations.

Key responsibilities

• Design and build the ML/LLM pipeline for data ingestion, knowledge extraction, retrieval, and reasoning.
• Create datasets, metrics, and pipelines that deliver measurable system improvements.
• Architect and enhance agents for context retrieval, knowledge extraction, and data alignment, including prompt engineering, model selection, and inference optimization.
• Establish MLOps practices such as orchestration, observability, and experiment tracking.
• Collaborate with engineering teams on system design and with JetBrains Research on the research agenda.
• Define hiring criteria, grow the ML team, and shape its culture.

Required profile

• Proven track record as an ML/AI lead.
• At least five years of experience in ML/AI systems, with two years focused on LLMs and generative AI.
• Deep understanding of the LLM ecosystem, including model architectures and fine‑tuning approaches.
• Hands‑on experience with prompt engineering, LLM pipeline design, and evaluation.
• Strong communication skills and fluency in English.

Required skills

• Python
• Kotlin (optional)
• Prompt engineering
• LLM pipeline design
• Agentic frameworks (e.g., LangChain, LlamaIndex, LangSmith, smolagents)
• Vector databases
• Retrieval‑augmented generation (RAG) patterns
• Deploying and scaling LLM‑powered applications via OpenAI, Anthropic or open‑source models
• MLOps tools for orchestration, observability, and experiment tracking