Large Language Model (LLM) Engineer

About the position Large Language Model (LLM) Engineer Remote, Work from Home US Citizen, with the ability to obtain and maintain up to Top-Secret Clearance (TS/SCI) @Orchard LLC is supporting a leader in AI/ML Software Development of products for the Federal Government operating at the unique intersection of advanced AI software development and vital national security missions. We are looking for an LLM Engineer to focus on multi-agent data integration products, ensuring they have minimal friction and maximum impact on government clients, including National Security and Intelligence Community missions. This is an opportunity to be part of inventing a whole new class of software products.

Responsibilities

• Suggest ways requirements can be met via search, machine learning, and other data science methods
• Decompose AI problems into solvable pieces and translate those solutions into code
• Prepare design specifications, conceptual diagrams, process flows, data models, prototypes, user interface designs, use cases, screen layouts, test plans, deployment plans, and system documentation
• Train and validate models and knowledge graphs, often in big data, distributed environments
• Perform model introspection to understand and explain model behaviors
• Integrate models into operational systems, including performing prompt engineering and domain-specific refinement, coordinating multiple agents, and optimizing performance
• Efficiently develop software capabilities using industry standards and repeatable processes, helping projects stay within budget and on schedule
• Review and test software for functionality and adherence to the design requirements, and document test results
• Determine the efficacy of your projects through repeatable, quantifiable means like industry-standard benchmarking
• Educate others on the capabilities of your projects via demonstrations, tutorials, or other means
• Work well within a team environment and communicate effectively with both technical and non-technical stakeholders
• Stay up to date with developments in the field and continually learn how to apply the latest relevant advancements
• Lead trade studies, analyses of alternatives, and assessments of existing systems

Requirements

• Minimum of a bachelor’s degree and 12 years of experience in a science or engineering field
• Minimum of 8 years of software development experience with Java, Python, and SQL
• Due to the nature of this position and the information that employees will be required to access, U.S. Citizenship is required.
• Must have deep understanding of how transformer models and latent spaces work, and techniques for manipulating both.
• Significant, demonstrable experience implementing retrieval augmented generation (RAG) and using various prompt engineering techniques, especially reflection, prompt chaining, reason and act (ReAct), and chain of thought
• Experience performing data engineering tasks using a platform like Oracle Cloud Infrastructure (OCI) Data Integration or Data Flows, Amazon Web Services (AWS) Glue, Informatica, Talend, or similar.
• Ability to describe the data assumptions and processing steps of common machine learning methods, and which methods are appropriate for a variety of use cases
• Deep understanding of transformer architectures and foundation model training and operations
• Expertise with ML libraries, like Scikit-learn, TensorFlow, PyTorch, LangGraph, and LlamaIndex
• Deep understanding of embedding techniques and prompting best practices
• Strong problem-solving skills
• Strong written and oral communication skills
• Able to work independently and self-identify tasks
• Ability to review and maintain existing code and applications
• Ability to research and evaluate new concepts and processes to improve performance

Nice-to-haves

• Data Scientist background
• Ability to obtain and maintain a TS/SCI clearance
• Experience with Spark, Elasticsearch, Containers, and Kubernetes; or related vector/graph databases and distributed processing platforms
• Familiarity with deploying data and processing in commercial clouds like Oracle Cloud Infrastructure (OCI), Amazon Web Services (AWS), Google Cloud, and Microsoft Azure
• Familiarity with visualization tools like Qlik, Tableau, Plotly, Kibana, and Matplotlib

Benefits

• Join a dynamic, rapidly growing team at the forefront of AI and data integration.
• Work on innovative multi-agent solutions for critical government missions.
• Make a significant impact on how government agencies leverage data for decision-making and operational efficiency.
• Thrive in a collaborative, supportive work environment focused on innovation and customer success.

Apply tot his job Apply To this Job