Founding ML Engineer (Spectrum)
软件工程师和人工智能代理都面临着同样的问题：找到一个回答他们难以解决的个人或地点。许多解决方案承诺通过向量数据库中的相似性搜索来解决这一问题。不幸的是，寻找答案往往是拼图，需要在无数矛盾来源中收集碎片，并且不能没有手术搜索和仔细推理就解决。谱集从组织的代码，文档和问题中收集数据，并将知识组建成统一的解剖学，这些 AI 代理可以有效地搜索和推论。我们的目标是彻底改变软件构建组织的语义层空间，超越与代码失调的规格，引入一个活着的规范从整个系统中提取并用来保持一致。谱系旨在成为所有产品和建筑知识的唯一来源。谱系是一个 JetBrains 创业化器的居民，具有启动速度和自主性，并且得到了25年的开发工具专业知识。我们正在寻找一名顶级 ML 工程师来帮助我们塑造软件开发的未来。你将拥有我们的 AI 和 ML 工程堆，并帮助定义我们的团队研究议程。你的技术视觉和设计决策将直接塑造产品并决定其成功。你的责任包括：· 为数据摄入，知识提取，检索和后续推理设计和构建 ML/LLM 解决方案。· 创建系统中可测量的改进的数据集，指标和管道。· 架构和改善环境检索，知识提掘和数据调整代理，其中包括快速工程，模型选择和推断优化。· 建立 MLOP 实践，包括编排，可观察性和实验跟踪。·与工程团队合作，设计系统和 JetBrains Research 在研究议程上。·确定招聘标准，发展 ML 团队，塑造 ML 团队文化。我们希望你拥有：·作为 ML/AI 领导者经验证明的历史记录。·至少五年的 ML/AI 系统经验，以 LLM 和生成人工智能专注于至少两年。·深入了解 LLM 生态系统，包括模型架构和细节调整方法。·实践经验：·快速工程和 LLM 管道设计，包括评估。
查看英文原文
Software engineers and AI agents alike suffer from the same problem: finding that one person or place that will answer their tough, specific question. Many solutions promise to solve this with similarity search in vector databases. Unfortunately, finding the answer is often a puzzle with pieces to be collected across a myriad of contradictory sources and cannot be solved without surgical search and careful reasoning.
Spectrum collects data from an organization’s code, docs, and issues, and organizes knowledge in a unified ontology that AI agents can efficiently search through and reason over. We aim to revolutionize the semantic layer space for software-building organizations and move beyond specs that fall out of sync with code, introducing a living spec – one that’s extracted from the whole system and used to keep it aligned. Spectrum is meant to be the single source of truth for all product and architectural knowledge.
Spectrum is a resident of JetBrains' startup incubator, with startup speed and autonomy, and backed by 25 years of developer tooling expertise. We are looking for a top-class ML Engineer who will help us shape the future of software development. You will own our AI and ML engineering stack and help define the research agenda for our team. Your technical vision and design decisions will directly shape the product and determine its success.
Your responsibilities will include:
- Designing and building the ML/LLM solution for data ingestion, knowledge extraction, retrieval, and subsequent reasoning.
- Creating the datasets, metrics, and pipelines that drive measurable improvements across the system.
- Architecting and improving agents for context retrieval, knowledge extraction, and data alignment, which includes prompt engineering, model selection, and inference optimization.
- Establishing MLOps practices, including orchestration, observability, and experiment tracking.
- Collaborating with the engineering team on system design and with JetBrains Research on the research agenda.
- Defining hiring criteria, growing the ML team, and shaping the ML team culture.
We expect you to have:
- A proven track record as an ML/AI Lead.
- 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 – Kotlin knowledge would be a plus.
- Excellent communication skills, with the ability to explain complex technical concepts to diverse audiences.
- Proficiency in English, both written and verbal.
Our ideal candidate would have:
- Experience with ontologies, knowledge graphs, or graph-based reasoning.
- Experience in early-stage startups – you enjoy the zero-to-one phase.
- The ability to think strategically about product-led AI, beyond just training models in isolation.
- A background in code analysis, developer tools, or software engineering research.
- Experience with multi-agent systems or complex agentic workflows.
- Actively contributed to relevant open-source projects or publications.
What we offer
- A competitive salary and JetBrains benefits.
- A generous runway and corporate resources with startup autonomy.
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.
Originally posted on Himalayas