Senior AI Engineer

Analytica•Bethesda, MD

About The Position

We are seeking an experienced Senior AI Engineer to build retrieval, semantic search, summarization, and source-traceable AI application capabilities for a Federal data analytics and AI modernization initiative. The team will deliver a secure, scalable platform that integrates structured and unstructured data, provides data visualization and traceable AI-assisted analytics, and gives examiners centralized tools for search, review, monitoring, and decision support. The platform will support professional judgment and will not replace authoritative agency financial or grants-management systems or execute financial transactions. Analytica has been recognized by Inc. Magazine as the fastest-growing private US small business. We work with U.S. government customers in health, civilian, and national security missions. As a core member you’ll work with a diverse team of professionals to solve matters, architect nuisances, and come up with alternatives.

Requirements

Hands-on experience developing applications using LLMs, RAG, semantic search, or generative AI.
Experience building AI services for search, summarization, document analysis, question answering, or decision support.
Strong Python and API development skills.
Experience with embeddings, vector search, retrieval, prompt orchestration, and LLM evaluation.
Experience implementing source citation, grounding, traceability, and output validation.
Experience implementing AI guardrails, access controls, logging, monitoring, and error handling.
Experience integrating AI/LLM services with databases, APIs, search platforms, and data pipelines.
Strong technical communication, documentation, problem-solving, and cross-functional collaboration skills.
U.S. citizenship and ability to obtain and maintain Top Secret eligibility.
Active Top Secret clearance highly preferred.

Nice To Haves

Experience developing AI/LLM solutions for Federal financial, grants, budget, payment, award oversight, or financial reporting data.
Experience deploying AI applications in secure Federal, on-premises, cloud, or hybrid environments.
Experience with open-source LLMs and AI/ML frameworks.
Experience with vector databases, semantic search engines, or hybrid search architectures.
Experience with Linux.
Familiarity with PostgreSQL and/or Microsoft SQL Server.
Experience with Kubernetes and/or Rancher.
Familiarity with Jenkins, self-hosted Azure DevOps, and CI/CD pipelines.
Familiarity with Java and/or .NET applications and API integrations.
Experience with LLM observability, evaluation frameworks, prompt/version management, and AI application lifecycle management.
Familiarity with AI security, model governance, responsible AI, and data protection practices.

Responsibilities

Develop LLM-powered applications for retrieval, semantic search, summarization, document analysis, and decision support.
Build and integrate RAG pipelines, embeddings, vector search, and semantic retrieval capabilities.
Develop Python-based APIs and AI application services for production environments.
Implement prompt orchestration, context management, evaluation, source citation, and output grounding.
Implement guardrails, access controls, authentication, logging, error handling, and output validation.
Evaluate and optimize AI applications for accuracy, relevance, groundedness, latency, and reliability.
Integrate AI services with databases, search platforms, APIs, and existing data pipelines.
Troubleshoot and optimize LLM, retrieval, API, and AI application workflows.
Develop technical documentation for AI architecture, retrieval workflows, APIs, evaluation methods, and operational procedures.
Collaborate with AI/ML, data engineering, data science, and software engineering teams throughout development and testing.
Apply security, privacy, accessibility, data governance, and records-management requirements to AI applications.