Senior AI Full Stack Engineer

PRECISE SOFTWARE SOLUTIONS INCORPORATED•Washington, DC

3d•Onsite

About The Position

Precise Software Solutions Inc. is seeking a Senior AI Full Stack Engineer to serve as the lead technical executor for a Generative AI engineering program supporting the federal government. You will build, integrate, test, deploy, and operate secure AI-enabled applications, and you will own the program's core build, test, and pipeline deliverables. You will work hands-on across the full stack, from accessible user interfaces to APIs, RAG pipelines, and agentic workflows, and you will lead AI security testing and serve as the senior escalation point for production issues. Must be a U.S. citizen or lawful permanent resident (green card holder). Must reside in the Washington, DC metropolitan area and be able to work on-site at DC Government offices. Must be able to pass and maintain a Government background investigation.

Requirements

Bachelor's degree in Engineering, Computer Science, Systems, or a related scientific/technical discipline and 5+ years of relevant experience.
5+ years of hands-on experience in AI/ML engineering, AI-enabled application development, data engineering, cloud engineering, or software engineering, including direct development, integration, testing, and operational support of AI-enabled systems.
1+ year of hands-on experience with Generative AI, LLM integration, RAG, model evaluation, agentic AI, or production AI systems.
Strong proficiency in Python and experience developing AI-enabled applications, APIs, services, and automation.
Experience designing and deploying RAG pipelines, semantic retrieval, vector databases, cloud-based AI services, and AI workflow orchestration.
Knowledge of AI testing, model evaluation, Responsible AI practices, and AI security controls in secure enterprise or federal cloud environments.
Experience conducting AI-specific and adversarial testing (prompt injection, jailbreak, data poisoning) and documenting mitigations.
Experience developing AI-enabled user interfaces that conform to Section 508 / WCAG 2.1 A and AA.
Experience supporting release management, documentation, monitoring, and operational support.
At least one current Generative AI or Machine Learning certification, such as Microsoft Azure AI, AWS, Google Cloud, Databricks, NVIDIA, or CAIP, or an equivalent.
Must be a U.S. citizen or lawful permanent resident (green card holder).
Must reside in the Washington, DC metropolitan area and be able to work on-site at Government offices.
Must be able to pass and maintain a Government background investigation.

Nice To Haves

Master's degree in a related field and 7+ years of experience, including federal agency programs.
Experience with a modern front-end framework (e.g., React or Angular with TypeScript) and with containers (Docker/Kubernetes) and CI/CD tooling.
Experience with agentic AI frameworks (e.g., LangGraph, LlamaIndex, Semantic Kernel), MCP, and open-weight model serving (e.g., vLLM, TGI).
Experience in FedRAMP High or GovCloud environments and with SBOM formats (CycloneDX or SPDX).
Experience with AI-assisted accessibility remediation or document processing (OCR, PDF tagging).
A current, favorably adjudicated federal background investigation.

Responsibilities

Design, develop, integrate, deploy, and enhance AI-enabled applications, services, and user interfaces.
Build and maintain LLM integrations, Retrieval-Augmented Generation (RAG) pipelines, embeddings, vector search, agentic workflows, and AI-enabled automation.
Implement prompt and context engineering, structured outputs, model orchestration, and retrieval quality controls such as chunking, hybrid retrieval, relevance scoring, and grounding validation.
Ensure AI-enabled applications and interfaces meet security, privacy, and Section 508 / WCAG 2.1 A and AA accessibility requirements.
Implement model evaluation, hallucination reduction, retrieval quality tuning, monitoring, and performance optimization, including side-by-side comparisons for model upgrades.
Plan and oversee unit, integration, functional, regression, performance, load, accessibility, adversarial, model-quality, and user acceptance testing.
Conduct AI-specific security and adversarial testing (prompt injection, jailbreak, data poisoning, unsafe output, unauthorized disclosure) before each release, and document and mitigate findings.
Maintain the RAG knowledge-base refresh schedule and escalate any retrieval-relevance decline.
Enforce promotion controls across environments, including security scans, unit tests, and TEVV gates, with secrets kept in Government-furnished vaults.
Support MLOps workflows, including model versioning, drift detection, retraining, and release documentation.
Prepare release packages and Software Bills of Materials (SBOMs), and support ATO, security assessment, and vulnerability remediation activities.
Serve as a Tier 2 / Tier 3 helpdesk escalation resource, reachable within business hours and providing escalation support for critical and high-severity incidents.
Support production operations, root-cause analysis, issue triage, and continuous improvement.
Conduct code and prompt reviews, mentor developers, and act as the primary technical backup for the Lead AI Engineer.

Benefits

Comprehensive Health Benefits (Medical, Dental and Vision)
Flexible Spending Accounts (FSA) & Health Savings Account (HSA)
Retirement Plan with 4% match and discretionary match at year end
Paid Time Off (PTO): 15 days of PTO accrued per year; 7 holidays+ 3 Floating holidays; 2 Innovation days (paid training days)
Short Term and Long-Term Disability
Paid Parental Leave
Paid Jury Duty leave
Life and AD&D Insurance
Critical Illness Insurance
Training and Development
Wellness Incentives & Discount programs
Employee Referral Program
Annual Charity Donation Match
Awards and Recognition