Solutions Architect Principal

General Dynamics Information Technology • Albany, NY

2d • $144,500 - $195,500 • Hybrid

About The Position

GDIT is hiring a Solutions Architect Principal to provide technical direction for artificial intelligence and agentic engineering supporting the New York State Department of Health Medicaid Management Information System (MMIS) program. The role focuses on designing, building, and governing agentic AI systems for the eMedNY enterprise in Albany, NY, within a large Medicaid claims-processing environment subject to stringent response-time and continuous-availability service-level agreements and HIPAA/HITECH and FedRAMP obligations.

As an individual contributor, the Solutions Architect will architect, build, and operate multi-agent systems; develop their tool and context layers; establish evaluation, observability, performance, cost, reliability, security, and safety practices; and assess models, frameworks, and vendors. The position also produces reference architectures and other technical artifacts, participates in architecture reviews, and raises engineering capability through pairing, design review, standards, and mentorship. The role may be hybrid for someone local to Albany, NY, or 100% remote.

Requirements

• Bachelor’s degree in Computer Science, Software Engineering, Mathematics, or a related technical field.
• At least 8 years of professional software engineering or systems architecture experience.
• At least 1 year building and operating production large language model systems, including taking at least one agentic system to production and supporting it afterward.
• Expert-level Python and working fluency in a second language such as TypeScript, Java, Go, or Rust.
• Experience with agentic patterns and runtimes, including tool and function calling, Model Context Protocol, structured output, multi-agent orchestration, durable state, and human-in-the-loop control flow.
• Experience with Amazon Bedrock, Anthropic Claude, and agentic coding harnesses such as Claude Code.
• Knowledge of retrieval-augmented generation, including embeddings, hybrid retrieval, reranking, and vector stores such as pgvector or Amazon OpenSearch.
• Experience with evaluation and observability for non-deterministic systems; AWS cloud-native services, containers, Terraform or Terragrunt, and GitLab CI/CD.
• Knowledge of AI security and compliance, including prompt injection, insecure output handling, PHI leakage prevention, HIPAA/HITECH, NIST AI RMF, and the OWASP Top 10 for LLM Applications.
• Strong computer science fundamentals and ability to evaluate new frameworks, assess production readiness, and apply them effectively.
• Demonstrated rapid, self-directed learning and ability to explain how an unfamiliar technology was brought to production within a year.
• Sound engineering judgment and intellectual honesty about AI capabilities, including assessing model reliability and communicating when a solution is not ready.
• Comfort working without an established playbook and creating standards, tooling, and documentation.
• Ability to reason rigorously about determinism and blast radius, including which agent decisions can be autonomous, require human approval, or must not be delegated to a model.
• Excellent technical writing and ability to work with non-technical program and client stakeholders.
• Effectiveness as an individual contributor who influences through architecture, reference implementations, and mentorship.

Nice To Haves

• Advanced degree in Computer Science, Machine Learning, or Artificial Intelligence.
• Open-source contributions to AI or agent tooling, published evaluations, or technical writing in agentic engineering.
• Healthcare or Medicaid/MMIS domain experience, including X12 EDI transaction sets and HL7 FHIR.
• Certifications such as AWS Certified Machine Learning Engineer, AWS Certified Solutions Architect – Professional, or CISSP.

Responsibilities

• Architect, build, and operate multi-agent systems with planning, tool use, memory, and reflection loops as governed, auditable, and reproducible delivery-pipeline steps.
• Design and implement the tool and context layer, including Model Context Protocol servers, tool and output schemas, retrieval pipelines, and context-engineering standards.
• Build evaluation harnesses, including evaluation sets, scoring rubrics, and regression suites, to assess whether non-deterministic systems improve.
• Own performance, cost, and reliability for AI workloads, including tracing, token and spending budgets, model selection and routing, fallback behavior, and caching.
• Establish guardrail and safety architecture, including PHI stage gates, prompt-injection and data-exfiltration defenses, least-privilege tool scoping, and human-in-the-loop approval checkpoints.
• Evaluate models, frameworks, and vendors through evidence-based bake-offs, publish results, identify lock-in and failure modes, and recommend against adoption when warranted.
• Produce reference architectures, interface requirement documents, design patterns, and decision records, and defend them in architecture review boards.
• Mentor and raise engineering standards through pairing, design review, and guidance on applying AI to protected health information.
• Work directly with non-technical program and client stakeholders and create technical documentation and standards.

Benefits

• Comprehensive benefits and wellness packages.
• 401(k) with company match.
• Competitive pay and paid time off.
• Full-flex work weeks where possible.
• Medical plan options, including some with Health Savings Accounts.
• Dental and vision plan options.
• Vacation, sick and personal time, holiday, paid parental, military, bereavement, and jury duty leave.
• Short- and long-term disability benefits.
• Life, accidental death and dismemberment, personal accident, critical illness, and business travel and accident insurance provided or available.
• AI-powered career tool identifying career steps and learning opportunities.
• Internal mobility team focused on career goals.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior