AI/ML文档处理开发工程师,远程
AI/ML Document Processing Developer, Remote
AI/ML 文档处理开发者,远程办公
- 合同制
- 100% 远程
- 由于我们的政府客户要求,我们只能考虑美国公民或绿卡持有者。
- 候选人必须愿意并能够获得 CMS T4 公共信任许可。
- 必须是美国人员,并且在过去五年中至少有三年居住在美国。
- 请勿通过第三方招聘机构推荐!候选人必须自行申请。
作为 AI/ML 文档处理开发者,你将构建和运营使用 AWS Bedrock 对高容量文档集进行分类和数据提取的后端服务和批处理流程。你将负责整个流程:S3 数据摄入、多格式解析、LLM 和基于规则的分类、OCR 备用方案,以及围绕准确性、成本和吞吐量的工具。
- 构建 AI 非结构化数据文档扫描流程
- 处理多种非结构化的医疗提供方和健康保险数据文件,涵盖多种文档格式
- 提取用于业务逻辑和数据验证的关键数据元素
- 将非结构化文档扫描结果转换为可用的结构化业务数据
教育背景:
· 本科及以上学历
所需经验:
· 在 AWS 上有 5 年以上开发 RESTful 服务和事件驱动后端的经验
所需技术技能:
- 熟悉 AWS Bedrock 或类似 LLM 平台,包括提示工程、结构化输出、模型选择和令牌/成本管理
- 在 AWS 上有实际生产经验:S3、Lambda、ECS/Fargate 或 Batch、ECR、IAM、KMS 和 CloudWatch
- 有开发 RESTful 服务和事件驱动后端的经验
- 精通 Python,包括对高吞吐量批处理工作负载的并发处理
- 文档和文本处理:PDF、DOCX、电子邮件格式;使用 Textract、Tesseract 和/或其他类似工具进行 OCR
- 关系型和非关系型数据库,如 Postgres 和 DynamoDB,以及使用 Redis 的缓存
- 使用 Git、Jenkins 和/或 GitHub Actions 等 CI/CD 工具进行 Docker 镜像构建和部署
- 使用 pytest 和/或等效工具进行单元测试和代码覆盖率
所需技能和能力:
- 熟悉敏捷开发和工具,包括 JIRA
- 具备良好的沟通能力,能够向不同层级/技能水平的人员展示想法,包括内部和外部人员。
- 为 bug 修复、功能增强和操作指导提供技术支持和最终用户故障排除。
- 具备多任务处理能力
查看英文原文
AI/ML Document Processing Developer, Remote
- Contract
- 100% Remote
- Due to our government client requirements, we can only consider US Citizen or a Green Card holders for this position.
- Candidate must be willing and able to obtain a CMS T4 Public Trust clearance.
- Must be a US Person and have lived in the United States at least three (3) out of the last five (5) years.
- NO THIRD PARTY RECRUITERS PLEASE! CANDIDATES MUST BE SELF-REPRESENTED.
As an AI/ML Document Processing Developer, you will build and operate backend services and batch pipelines that classify and extract data from high-volume document sets using AWS Bedrock. You will own the pipeline end to end: S3 ingestion, multi-format parsing, LLM and rules-based classification, OCR fallback, and the tooling around accuracy, cost, and throughput.
- Build AI unstructured data document scanning pipeline.
- Process a variety of unstructured healthcare provider and health insurance data files across many different document formats.
- Extract key data elements to be used for business logic and data validation.
- Convert unstructured document scanning results into useable structured business data.
Education:
· Bachelor's degree or higher
Required Experience:
· 5+ years of experience developing RESTful services and event-driven backends in AWS
Required Technical Skills:
- Hands-on experience with AWS Bedrock or comparable LLM platforms, including prompt engineering, structured output, model selection, and token/cost management
- Production experience with AWS: S3, Lambda, ECS/Fargate or Batch, ECR, IAM, KMS, and CloudWatch
- Experience developing RESTful servicesandevent-driven backends
- Strong Python, including concurrent processing for high-throughput batch workloads
- Document and text processing: PDF, DOCX, email formats; OCR using Textract, Tesseract, and/or similar tool
- Relational and NoSQL databases, such as Postgres and DynamoDB, and caching using Redis
- Docker image builds and deployment through CI/CD such as Git, Jenkins and/or GitHub Actions
- Unit testing and code coverage using pytest and/or equivalent
Required Skills and Abilities:
- Hands-on experience with agile development and tools, including JIRA
- Strong communication skills with the ability to present ideas to various levels/skillsets, both internally and externally.
- Provide technical assistance and end user troubleshooting for bug fixes, enhancements, and how-to assistance.
- Ability to multitask between multiple projects and both business and technical stakeholders.
Preferred Skills:
- Healthcare Service Industry or Center for Medicare and Medicaid Services (CMS) experience
- Experience measuring and improving model output quality (ground-truth data sets, precision/recall, A/B comparisons, prompt iteration based on error analysis)
- Experience with hybrid architectures combining deterministic rules with LLM inference
- Experience handling PII/PHI under HIPAA or similar (VPC isolation, encryption, least-privilege IAM, audit logging)
- Experince with Healthcare claims, insurance, or other regulated document workflows
- Salesforce data integration
- SQL analytics environments (Snowflake, Redshift) for pipeline reporting and validation
- Infrastructure as code (Terraform, CDK, CloudFormation)
- Active AWS certification(s)
Please Note:
- Only those individuals selected for an interview will be contacted.
- No calls, inquiries, or Third-Party Vendors please.
- We are an equal opportunity employer. We encourage applications from candidates of all backgrounds and experiences. (The ACI Group is unable to sponsor H1B Visas).
- $1000 Referral Bonus - www.aci.com.
Since 1988, The ACI Group, a Baltimore-based staffing firm, has been committed to hiring the industry's leading professionals, and presenting exciting career opportunities. We have access to varied types of contract, permanent and contract-to-perm positions and offer a choice of employment options including a full benefits package.
Originally posted on Himalayas