DSCA AI Engineer - Generative AI, RAG & Agentic Systems (Software Development Analyst) - 30714

HII's Mission Technologies division•Arlington, VA

23d•$160,000 - $175,000•Remote

About The Position

HII’s Warfare Systems business group within its Mission Technologies division is seeking an experienced AI/RAG Engineer to design, build, and optimize secure generative AI, retrieval-augmented generation (RAG), agentic, and AI-governance capabilities for an enterprise application in an AWS GovCloud IL4/IL5 environment. The engineer will lead development of the AI intelligence layer, including data ingestion, retrieval, model integration, prompting, agent workflows, evaluation, AI gateway configuration, and AI security. The role partners with front-end, back-end, platform, cybersecurity, and Department of War identity teams to deliver dependable production AI capabilities. The position is fully remote and must align with Eastern Time Zone core business hours. It may require less than 10% travel to customer meetings on the East Coast. The role is classified as Software Development 3 or Software Development 4, with the level and salary based on background, direct experience, and education. Relevant experience requirements vary by education: for Software Development 3, five years with a related bachelor’s degree, three years with a related master’s, zero years with a related PhD, or nine years with a high school diploma or equivalent; for Software Development 4, nine years with a related bachelor’s, seven years with a related master’s, four years with a related PhD, or 13 years with a high school diploma or equivalent. An active Secret clearance must be held and maintained at the time of consideration. The stated anticipated salary range is $160,000 to $175,000. HII offers medical, dental, and vision plan choices; wellness resources; employee assistance programs; 401(k) savings plan options; financial planning tools; life insurance; employee discounts; paid holidays and paid time off; tuition reimbursement; and early-childhood and post-secondary education scholarships. Bonus or other non-recurrent compensation may occasionally be offered for qualified positions, if applicable.

Requirements

Strong Python development experience.
Experience building and operating production generative AI, RAG, or AI-enabled applications.
Strong understanding of large language models, embeddings, vector search, retrieval patterns, prompt design, structured outputs, and AI service APIs.
Experience designing RAG pipelines and integrating models with enterprise data sources, tools, APIs, or application services.
Experience developing or evaluating agentic workflows that use models, retrieval, and approved tools to complete bounded tasks.
Hands-on experience with Amazon Bedrock, Boto3, and AWS cloud services.
Experience evaluating and improving AI capabilities for quality, groundedness, latency, reliability, security, and cost.
Experience implementing practical AI security and governance controls, including prompt-injection mitigation, input and output validation, access-control integration, rate limiting, usage monitoring, logging, and data protection.
Experience with Git-based development, automated testing, and collaborative software-delivery practices.
Must possess and maintain an active Secret clearance at the time of consideration.
Must be able to align with Eastern Time Zone core business hours and work assigned East Coast core business hours.
Relevant experience and education requirement for Software Development 3: five years with a related bachelor’s degree, three years with a related master’s degree, zero years with a related PhD, or nine years with a high school diploma or equivalent.
Relevant experience and education requirement for Software Development 4: nine years with a related bachelor’s degree, seven years with a related master’s degree, four years with a related PhD, or 13 years with a high school diploma or equivalent.
Ability to remain stationary for prolonged periods while working at a computer; operate a keyboard, mouse, and standard office equipment; communicate effectively in virtual meetings, briefings, and secure collaboration environments; and review, analyze, and interpret digital data for extended periods with attention to detail and accuracy.
Must maintain a home work environment meeting company and government security requirements, including a controlled space for handling sensitive or FOUO information if applicable.

Nice To Haves

Eight or more years of preferred experience.
Experience with Amazon Bedrock AgentCore or comparable agent-runtime, orchestration, memory, tool-connectivity, or observability platforms.
Experience with LiteLLM or comparable AI gateway, model-proxy, or AI-governance platforms supporting multi-model routing, access controls, budgets, observability, and auditability.
Experience working in AWS GovCloud or other federal, defense, intelligence, or regulated cloud environments.
Experience with OpenSearch, pgvector, or comparable vector-search and retrieval platforms.
Familiarity with AWS CDK, CloudFormation, Terraform, or equivalent infrastructure-as-code tools.
Familiarity with DoW identity and access-management concepts, Zero Trust principles, least-privilege IAM, and secure service-to-service communication.
Familiarity with DISA STIGs, SRGs, RMF activities, security-control evidence, continuous monitoring, or vulnerability-remediation workflows.
Experience with LangChain, LlamaIndex, MCP-compatible tool integrations, or comparable AI orchestration frameworks.
Experience working with controlled, sensitive, or otherwise regulated data in a federal, defense, intelligence, or similarly regulated environment.

Responsibilities

Design, develop, and optimize production generative AI, RAG, and agentic capabilities using approved Amazon Bedrock services.
Evaluate and integrate foundation models based on quality, relevance, latency, reliability, security, and cost.
Build and improve RAG pipelines, including ingestion, preprocessing, chunking, embeddings, vector search, retrieval, reranking, and context generation.
Design agentic workflows combining foundation models, retrieved knowledge, approved tools, and enterprise APIs for bounded multi-step tasks.
Develop prompts, structured-output patterns, tool or function-calling interfaces, and application-appropriate guardrail configurations.
Establish AI evaluation methods, test datasets, and monitoring approaches for response quality, groundedness, accuracy, safety, tool-use outcomes, latency, reliability, and cost.
Develop knowledge-ingestion pipelines for structured and unstructured data while preserving source-level access controls and applicable data-handling requirements.
Implement AI security controls, including prompt-injection defenses, input and output validation, data protection, audit logging, and human-review or escalation workflows when required.
Design and administer AI gateway configurations, including model routing and allowlists, service-identity or virtual-key controls, rate limits, budgets, usage attribution, fallback behavior, logging, and guardrail integration.
Develop Python-based AI services, APIs, and integration patterns for backend application services.
Partner with platform teams on infrastructure-as-code, deployment, observability, and operational support for AI/RAG services, AI gateways, ingestion pipelines, vector-search capabilities, and supporting AWS resources.
Collaborate with backend, front-end, cybersecurity, platform, and identity teams to integrate secure and dependable AI capabilities into production applications.

Benefits

Medical insurance plan choices
Dental insurance plan choices
Vision insurance plan choices
Wellness resources
Employee assistance programs
401(k) savings plan options
Financial planning tools
Life insurance
Employee discounts
Paid holidays
Paid time off
Tuition reimbursement
Early-childhood and post-secondary education scholarships
Bonus or other non-recurrent compensation may occasionally be offered for qualified positions, if applicable