23 hours ago
Albany, NY, USAStaff+

Base Salary

$145k - $196k/yr

Responsibilities

  • Architect, build, and operate governed, auditable multi-agent systems with planning, tool use, memory, reflection, and durable execution patterns.
  • Design the agent tool and context layer, including Model Context Protocol servers, schemas, retrieval pipelines, and context-engineering standards.
  • Build evaluation harnesses with evaluation sets, scoring rubrics, and regression suites for non-deterministic AI systems.
  • Own AI workload performance, cost, reliability, tracing, token and spend budgets, model routing, fallback behavior, and caching.
  • Establish AI safety architecture covering PHI stage gates, prompt-injection and data-exfiltration defenses, least-privilege tool access, and human approval checkpoints.
  • Evaluate models, frameworks, and vendors through bake-offs, documented results, and analysis of lock-in and failure modes.
  • Produce reference architectures, interface requirement documents, design patterns, and architecture decision records.
  • Influence and mentor engineers through pairing, design reviews, technical writing, and engineering standards.
  • Work directly with non-technical program and client stakeholders and defend designs in architecture review boards.

Requirements

  • Bachelor’s degree in Computer Science, Software Engineering, Mathematics, or a related technical field is required; an advanced degree in Computer Science, Machine Learning, or Artificial Intelligence is preferred.
  • 8+ years of professional software engineering or systems architecture experience, including at least 1 year building and operating production large language model systems.
  • At least one agentic system must have been taken to production and supported 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.
  • Experience with retrieval-augmented generation, 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 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, rapid self-directed learning, sound judgment about AI reliability and determinism, excellent technical writing, and comfort creating standards without an established playbook.
  • Preferred qualifications include open-source contributions to AI or agent tooling, published evaluations, technical writing in agentic engineering, healthcare or Medicaid/MMIS experience including X12 EDI and HL7 FHIR, and certifications such as AWS Certified Machine Learning Engineer, AWS Certified Solutions Architect – Professional, or CISSP.

Benefits

  • Hybrid work for candidates local to Albany, NY, or 100% remote work; full-flex work week where possible.
  • Comprehensive medical, dental, vision, HSA, disability, life, accident, critical illness, and business travel insurance options.
  • 401(k) plan with company match and pre-tax and post-tax contribution options.
  • Paid vacation, sick, personal, holiday, parental, military, bereavement, and jury-duty leave.
  • Internal mobility support, AI-powered career development tools, wellness packages, and an innovation-focused, military-friendly workplace.
  • Regular full-time schedule of 40 hours per week with no travel required.

Categories

Solutions Engineering
General Dynamics Information Technology

About General Dynamics Information Technology

10,000+ employees

General Dynamics Information Technology (GDIT) delivers enterprise IT, systems integration, cybersecurity, cloud, and software engineering services to U.S. federal agencies, including defense and intelligence organizations. It provides contract-based professional and managed services ranging from network operations and unified communications to training and simulation. GDIT is a business unit of General Dynamics (NYSE: GD) and is headquartered in Falls Church, Virginia.

Contact me