Senior AI/ML Engineer, Knowledge & Retrieval Systems

Onebrief is a revolutionary platform for military staff workflows and operational planning. The software is designed to enable smarter, real-time decisions. With unparalleled collaboration features, AI-enhanced tools, and customizable workflows, Onebrief makes staffs superhuman. The expanding roster of customers includes COCOMs and Service Components worldwide.

Founded in 2019 by a group of experienced planners, today, Onebrief’s workforce of 120+ spans veterans from all forces and global organizations, and technologists from leading-edge software giants. Onebrief’s growth is exemplary, having raised $53M+ and counting from leading venture investors.

We're seeking a Machine Learning Engineer with a deep understanding of information retrieval, knowledge representation, and edge-deployable ML systems.

In this role you will work toward transforming complex, interconnected military operational plans into actionable, queryable knowledge. You'll lead the design and implementation of scalable systems for chunking, indexing, and retrieving rich data from multiple modalities. Your solutions will enable fast, reliable information retrieval to augmented Generative AI systems.

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.

What You'll Do

• 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

Preferred

• 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

Compensation Range: $200K - $230K