Role overview
About Onebrief
Onebrief is collaboration and AI-powered workflow software designed specifically for military staffs. By transforming this work, Onebrief makes the staff as a whole superhuman - meaning faster, smarter, and more efficient.
We take ownership, seek excellence, and play to win with the seriousness and camaraderie of an Olympic team. Onebrief operates as an all-remote company, though many of our employees work alongside our customers at military commands around the world.
Founded in 2019 by a group of experienced planners, today, Onebrief’s team spans veterans from all forces and global organizations, and technologists from leading-edge software companies. We’ve raised $123m+ from top-tier investors, including Battery Ventures, General Catalyst, Insight Partners, and Human Capital, and today, Onebrief is valued at $1.1B. With this continued growth, Onebrief is able to make an impact where it matters most.
Role Overview
We're seeking a Machine Learning Engineer with a deep understanding of information retrieval, knowledge representation, and edge-deployable ML systems.
What we're looking for
Expect to architect hybrid retrieval pipelines that blend semantic search, keyword-based methods, and graph reasoning, optimize embeddings for specialized content, and build resilient systems that power rapid decision-making.
We're looking for someone with hands-on experience building real-world retrieval and knowledge-driven systems.
- Design and build hybrid retrieval systems that combine semantic, symbolic, and graph-based methods
- Develop pipelines to encode and retrieve operational knowledge using LLMs, vector databases, and custom chunking/indexing strategies
- Build and optimize retrieval-augmented generation (RAG) systems for high-stakes environments
- Architect knowledge graphs and integrate them into retrieval workflows
- Collaborate with ML, product, and domain experts to transform requirements into deployable solutions
Key Technologies
- Vector Databases, Hybrid Search Pipelines
- Embeddings & Transformer-based models
- Knowledge Graphs (Neo4j, RDF, SPARQL, custom schemas)
- Python, Distributed Systems, ETL pipelines
- Docker, Kubernetes, Edge Computing platforms
Required:
- B.S. in Computer Science, Engineering, or equivalent practical experience
- 2–4 years of experience in applied ML, information retrieval, or knowledge systems
- Strong Python programming skills
- Experience with semantic search, vector stores, and retrieval system design
- Comfort with ETL workflows and structured, domain-specific datasets
- Understanding of distributed systems and performance trade-offs
- Familiarity with testing and evaluating information retrieval systems
- Understanding of security considerations in data handling and system design
- Experience designing chunking/indexing pipelines for large, domain-specific datasets
- Experience designing or deploying knowledge graphs in real-world systems
- Experience with offline-capable and edge-deployable ML systems
- Familiarity with containerization and orchestration tools (Docker, Kubernetes)
- Exposure to geospatial data and reasoning systems
- Background in defense, national security, or other mission-critical domains
- Understanding of LLM prompt engineering, context window optimization, and RAG techniques
- Advanced degree (M.S. or PhD) in a relevant field is a plus
Working Style:
- First principles thinking with high ownership mentality
- Strong communication and collaboration skills
- Bias for action - you deliver working systems in imperfect conditions
- Comfortable working autonomously in a fast-moving startup environment