AI Solution Engineer

Our CompanyExplore how you can contribute at AmeriLife.For over 50 years, AmeriLife has been a leader in the development, marketing and distribution of annuity, life and health insurance solutions for those planning for and living in retirement.Associates get satisfaction from knowing they provide agents, marketers and carrier partners the support needed to succeed in a rapidly evolving industry.Job SummaryAmeriLife is a national leader in insurance and financial services, and we are standing up an enterprise AI capability from the ground up. The model is deliberately federated: a small, senior center owns the data platform, reusable AI services, and governance — while solution architects embedded in our Health and Wealth verticals find the highest-value work and build it alongside the business.This is one of the first of those embedded roles, and it is a builder’s job. You will spend most of your time engineering and shipping AI agents and LLM-powered services on Databricks and Azure — automating real workflows in contracting, commissions, and distribution operations where a national platform gives the economics real scale. The rest of your time draws on classic data science: the forecasting, propensity, and evaluation work that makes those solutions trustworthy and measurable.Job DescriptionRole BreakdownAgentic AI engineering & implementation: Designing, building, evaluating, and shipping multi-step AI agents and LLM-powered services into productionSolution architecture & business partnership: Finding and shaping high-value use cases with vertical leaders; reference architecture, reusable patterns, build-vs-buy inputApplied data science & ML: Forecasting, propensity and segmentation models, evaluation design, and the feature engineering behind both agents and modelsWhat You'll DoBuild and ship AI agentsDesign, build, and deploy multi-step AI agents that complete real business workflows — retrieving from governed data, calling internal APIs and tools, making bounded decisions, and escalating to a human when they should. Engineer the unglamorous parts that make agents work: tool and function definitions, retrieval and grounding strategy, state and memory, orchestration, retries and failure handling, cost and latency management. Build evaluation into the build, not after it. Golden datasets, offline and online evals, regression suites, human-in-the-loop review, and guardrails you can point at when someone asks how you know it works. Instrument and operate what you ship. Tracing, monitoring, drift and quality alerting, and a clear owner for every production surface. Harvest reusable components into the shared services catalog so the next solution costs less than yours did. Architect solutions with the businessEmbed with your vertical’s leaders — operations, distribution, affiliate partners — observing the actual work rather than waiting on a written spec. Translate business problems into solution designs, including the honest version: what is automatable today, what needs process work first, and what is not worth building. Establish reference architectures and preferred patterns for your vertical, and contribute them back to the center. Bring judgment to build-versus-buy and to the question of when an agent is the right answer versus a model, a rule, or a fixed process. Apply data science where it moves the outcomeBuild and validate predictive models — forecasting, propensity, segmentation, anomaly detection — that inform planning or drive an automated decision. Engineer features and pipelines on the Lakehouse that serve both your models and your agents. Design the measurement. Baselines, holdouts, A/B and quasi-experimental designs, and a defensible read on whether the thing actually worked. Communicate results plainly to audiences that range from engineers to distribution executives. Deliver responsibly in a regulated businessDocument intended use, limitations, training-data assumptions, testing approach, and monitoring plan for every model and agent you put into production, and keep the model inventory current. Apply de-identification and least-privilege access as defaults when working with PHI, financial, or Medicare-related data. Flag fairness and unfair-discrimination risk on anything touching underwriting, rating, or pricing, and route it for actuarial and compliance review. Build for auditability — reproducible code, documented lineage and methodology, and recordkeeping that holds up under HIPAA, FINRA, SEC, CMS, and state insurance requirements. Technical RequirementsAgentic AI Engineering & ImplementationRequired3+ years building AI or ML systems in production, including hands-on experience designing and shipping LLM-powered agents or multi-step AI workflows — not just consuming AI toolsPractical fluency with at least one agent framework or SDK (Claude Agent SDK, LangGraph, LangChain, Databricks Mosaic AI Agent Framework, Semantic Kernel, or similar) and the ability to reason about why you chose itTool and function calling: defining tools, wiring agents to internal APIs and data, and handling structured outputs reliablyRAG and grounding in practice — chunking and retrieval strategy, vector search, semantic and hybrid retrieval, and knowing when retrieval is the wrong answerPrompt and context engineering as an engineering discipline: versioned, tested, and evaluated rather than hand-tunedSystematic AI evaluation — building eval sets, measuring quality and regression, and implementing guardrails for accuracy, safety, and costSound judgment on traditional ML versus generative AI versus deterministic automation, and the trade-offs of eachPreferredHands-on work with Claude (Agent SDK, Claude Code, Model Context Protocol) and/or building on Microsoft Copilot — Copilot Studio agents, M365 Copilot declarative agents and extensibility, Copilot connectorsBuilding or consuming MCP servers to expose enterprise data and tools to agentsMulti-agent orchestration, human-in-the-loop workflow design, or long-running agent state managementDocument intelligence and unstructured-data extraction at scale (forms, contracts, statements)LLM fine-tuning or adaptation, and a clear-eyed view of when it beats prompting or retrievalDatabricks PlatformRequiredStrong hands-on Databricks experience — notebooks, clusters, jobs and Workflows, and developing production-grade code rather than one-off analysisAdvanced SQL and solid PySpark for large-scale transformation and feature engineering on a LakehouseUnity Catalog for governance, lineage, and access control; Delta Lake and medallion architecture patternsMLflow for experiment tracking, model registry, and deploymentPreferredDatabricks Mosaic AI — Agent Framework, Vector Search, Model Serving, AI Gateway, or Foundation Model APIsDelta Live Tables, Feature Store, Lakehouse Federation, or Databricks Asset BundlesDatabricks certification (Data Engineer Professional, ML Engineer Professional, or Generative AI Engineer Associate)Azure Cloud & Engineering FoundationsRequiredProduction experience on Microsoft Azure, including Azure OpenAI or Azure AI Foundry, and deploying services that other systems depend onStrong Python engineering practice: modular, tested, reviewable code with Git-based version controlAPI design and integration — REST, authentication and secrets handling, and integrating with enterprise systems of recordContainerization (Docker) and CI/CD for data and AI workloadsWorking understanding of cloud-native architecture, identity and RBAC, and data governance in a regulated environmentPreferredAzure Data Factory, Functions, API Management, Key Vault, Entra ID, Azure DevOps, or Logic AppsInfrastructure-as-code (Terraform, Bicep) and MLOps / LLMOps practiceAzure certification (AI Engineer Associate, Data Scientist Associate, or Solutions Architect Expert)Applied Data Science & Machine LearningRequiredSolid foundation in statistical modeling and machine learning, with the judgment to match the method to the business problemExperience building and validating supervised models on structured data (gradient boosting, regression, classification) and taking at least one to productionTime-series forecasting experience, and comfort with hypothesis testing and rigorous model evaluationComfort with imperfect real-world data — missing values, class imbalance, drift, and inconsistent source systemsPreferredClustering, anomaly detection, causal inference, uplift modeling, or Bayesian methodsExperiment design and measurement in an operational (non-web) settingOptimization or simulation applied to a business processSolution Architecture & Business PartnershipRequiredDemonstrated ability to work directly with non-technical business leaders — discovering opportunities, framing problems, and setting expectations honestlyFull production ownership from problem definition through deployment, adoption, and iterationExperience leading delivery at the project or pod level: planning, sequencing, and accountability for an outcomeClear written and verbal communication, including the ability to explain a technical trade-off to an executive in a paragraphPreferredInsurance, financial services, healthcare, or another regulated industry — Medicare distribution, life and annuity, producer contracting, or commissions especially relevantExperience in a federated or multi-affiliate organization where influence matters more than authorityConsulting, forward-deployed, or embedded-engineering backgroundTrack record of raising the technical bar around you — patterns, reviews, enablement, mentorshipOur Tech StackData & AI Platform: Databricks on Azure — Lakehouse, Unity Catalog, Delta Lake / Delta Live Tables, Mosaic AI (Agent Framework, Vector Search, Model Serving), MLflow, WorkflowsCloud: Microsoft Azure — Azure AI Foundry, Azure OpenAI, Functions, Data Factory, API Management, Key Vault, Entra ID, DevOpsAgent & LLM Tooling: Claude (Agent SDK, Claude Code, MCP), Microsoft 365 Copilot extensibility & Copilot Studio, LangGraph / LangChain, Model Context Protocol serversLanguages: Python, SQL, PySpark; TypeScript a plusML & DS: scikit-learn, XGBoost / LightGBM, statsmodels / Prophet-class forecasting, MLflow evaluationEngineering & DevOps: Git / GitHub, Docker, CI/CD, infrastructure-as-code, observability and eval harnessesEducation, Location, & TravelBachelor’s or Master’s in Computer Science, Data Science, Engineering, Statistics, Applied Mathematics, or a related technical field. Equivalent experience with a strong portfolio of shipped work is equally welcome — show us what you have built. 6–10 years of combined software, data, or AI/ML engineering experience, with at least 2 years hands-on with LLM-based systemsU.S.-based and remote-friendly. Expect periodic travel (roughly 15–25%) to AmeriLife business locations and affiliate sites — embedded means occasionally in the room. Must be authorized to work in the United States without sponsorshipCompensationSalary Range: $170,000 to $190,000Salary offers will vary commensurate with experience, education, skills, and training What AmeriLife OffersA comprehensive benefits package that includes PTO, medical, dental, vision, retirement savings, disability insurance, and life insurance.Equal Employment Opportunity StatementWe are an Equal Opportunity Employer and value diversity at all levels of the organization. All employment decisions are made without regard to race, color, religion, creed, sex (including pregnancy, childbirth, breastfeeding, or related medical conditions), sexual orientation, gender identity or expression, age, national origin, ancestry, disability, genetic information, marital status, veteran or military status, or any other protected characteristic under applicable federal, state, or local law. We are committed to providing an inclusive, equitable, and respectful workplace where all employees can thrive.Americans With Disabilities Act (ADA) StatementWe are committed to full compliance with the Americans with Disabilities Act (ADA) and all applicable state and local disability laws. Reasonable accommodations are available to qualified applicants and employees with disabilities throughout the application and employment process. Requests for accommodation will be handled confidentially. If you require assistance or accommodation during the application process, please contact us at HR@AmeriLife.com.Pay Transparency StatementWe are committed to pay transparency and equity, in accordance with applicable federal, state, and local laws. Compensation for this role will be determined based on skills, qualifications, experience, and market factors. Where required by law, the pay range for this position will be disclosed in the job posting or provided upon request. Additional compensation information, such as benefits, bonuses, and commissions, will be provided as required by law. We do not discriminate or retaliate against employees or applicants for inquiring about, discussing, or disclosing their pay or the pay of another employee or applicant, as protected under applicable law. Pay ranges are available upon request.Background Screening StatementEmployment offers are contingent upon the successful completion of a background screening, which may include employment verification, education verification, criminal history check, and other job-related inquiries, as permitted by law. All screenings are conducted in accordance with applicable federal, state, and local laws, and information collected will be kept confidential. If any adverse decision is made based on the results, applicants will be notified and given an opportunity to respond.