Solutions Architect Principal

General Dynamics Information Technology • Albany, NY

19h • Hybrid

About The Position

GDIT is hiring a Solutions Architect Principal to lead the architecture and engineering of agentic AI systems supporting the New York State Department of Health Medicaid Management Information System (MMIS) program and the eMedNY enterprise in Albany, New York. This individual contributor will set technical direction for how AI is designed, built, and governed in a large Medicaid claims-processing environment subject to stringent response-time and continuous-availability service-level agreements and HIPAA/HITECH and FedRAMP obligations. The role influences the program through architecture, reference implementations, and engineering mentorship.

The position is hybrid for candidates local to the Albany, NY area or 100% remote. It is a regular role with 40 scheduled hours per week and no travel required. The listed salary range is $144,500–$195,500; actual compensation may vary based on experience, location, and contractual requirements. GDIT describes its work as supporting government, defense, and intelligence customers, with 26,000 experts operating across more than 50 countries.

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 skills 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.
• Knowledge of 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 foundation and ability to learn unfamiliar frameworks, inspect their source, assess production readiness, and apply them in practice.
• Demonstrated rapid, self-directed learning, with the ability to describe a technology taken from unfamiliarity to production within a year.
• Sound engineering judgment and intellectual honesty about AI, including the ability to assess model reliability and advise leadership when a solution is not ready.
• Comfort working without an established playbook and creating needed standards, tooling, and documentation.
• Rigorous reasoning about determinism and blast radius, including determining which agent decisions may be autonomous, require human approval, or must not be delegated to a model.
• Excellent technical writing and ability to work directly with non-technical stakeholders.
• Ability to contribute as an individual contributor and influence 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.
• AWS Certified Machine Learning Engineer, AWS Certified Solutions Architect – Professional, or CISSP certification.

Responsibilities

• Architect, build, and operate governed, auditable, and reproducible multi-agent systems, including planning, tool use, memory, and reflection loops.
• Design and implement the tools and context layer for agents, including Model Context Protocol servers, tool and output schemas, retrieval pipelines, and context-engineering standards.
• Build evaluation harnesses, evaluation sets, scoring rubrics, and regression suites to measure whether non-deterministic systems improve.
• Own AI workload performance, cost, and reliability, including tracing, token and spending budgets, model selection and routing, fallback behavior, and caching.
• Establish AI guardrails 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 using evidence; conduct bake-offs, publish results, identify lock-in and failure modes, and recommend against adoption when appropriate.
• Produce and defend reference architectures, interface requirement documents, design patterns, and architecture decision records in architecture review boards.
• Mentor engineers through pairing and design reviews, and establish standards for applying AI to protected health information.
• Work directly with non-technical program and client stakeholders.

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, some with Health Savings Accounts.
• Dental plan options.
• Vision plan.
• Vacation, sick, personal, and holiday leave.
• 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.

What This Job Offers

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