
US_East | Data Engineer_L2
Datum Software · IL
Mixed hiring record · median 47 days open
Hiring signal
Actively hiring
Posted yesterday · still listed on the employer's own board · How we score
All reasons
- 48% of this employer's openings are over 60 days old
- This role has been posted 3 times
In its favour
- Posted yesterday
- Still listed on the employer's own board
Role Name
Data Engineer
Location
Hartford, CT
Job Description
Experience Required
- 4–8 years of experience in software engineering, data engineering, or machine learning (ML) engineering.
- 1–5 years of hands-on experience with Generative AI (GenAI).
Role Summary
We are seeking an experienced Data Engineer with expertise in Generative AI and Google Cloud Platform (GCP) to build, test, and deploy production-ready GenAI solutions for insurance clients.
The ideal candidate will develop solutions for document summarization, intelligent intake, underwriting and claims assistants, and agentic workflows. This role requires the ability to translate technical architecture into functional applications and take ownership of features from initial prototyping through production deployment.
Key Responsibilities
- Design, develop, and deploy GenAI applications using Gemini models on Gemini Enterprise Agent Platform and Vertex AI.
- Design and optimize prompts, structured outputs, and function calling for insurance-related documents, including submissions, ACORD forms, Certificates of Insurance (COIs), loss runs, and insurance policies.
- Develop Retrieval-Augmented Generation (RAG) pipelines using document chunking, embeddings, Vector Search, Vertex AI Search, grounding, and citations.
- Build AI agents using the Agent Development Kit (ADK), deploy them on Agent Engine, and integrate external tools and APIs.
- Implement document extraction and classification solutions using Document AI and Gemini multimodal capabilities.
- Develop and deploy scalable services using Cloud Run or Google Kubernetes Engine (GKE), expose APIs through Apigee, and implement CI/CD pipelines using Cloud Build.
- Manage data ingestion, processing, storage, and movement using BigQuery, Cloud Storage, Pub/Sub, and Dataflow.
- Create evaluation datasets and perform quality, latency, and cost assessments using GenAI evaluation services and golden datasets.
- Implement security guardrails, personally identifiable information (PII) masking using Sensitive Data Protection (DLP), safety filters, and least-privilege Identity and Access Management (IAM).
- Collaborate with QA, UI, and data engineering teams in Agile sprints to deliver high-quality solutions.
- Write clean, maintainable, well-tested, and thoroughly documented code.
Required Skills and Qualifications
- Strong programming experience with Python, including FastAPI or Flask, asynchronous programming, and pytest.
- Hands-on experience with the Gemini API, Vertex AI SDK, or Google Gen AI SDK.
- Strong understanding of RAG architecture and experience with at least one vector database or search solution, such as:
- Vertex AI Vector Search
- AlloyDB with pgvector
- BigQuery Vector Search
- Experience with LLM frameworks, including ADK, LangChain, or LangGraph.
- Practical knowledge of core GCP services, including:
- Cloud Run
- Cloud Functions
- Cloud Storage
- BigQuery
- IAM
- Secret Manager
- Experience with REST API design and development.
- Proficiency with Git, Docker, and CI/CD processes.
- Strong written and verbal communication skills, with the ability to collaborate effectively with onsite and client teams.
Preferred / Nice-to-Have Skills
- Experience in the insurance industry, including Property & Casualty (P&C), Excess & Surplus (E&S), specialty insurance, workers' compensation, or financial services.
- Experience with Document AI custom extractors and Optical Character Recognition (OCR) for scanned or handwritten documents.
- Familiarity with Agent2Agent (A2A) protocol or Model Context Protocol (MCP) for tool integration.
- Experience with model tuning, supervised fine-tuning of Gemini models, and model monitoring.
- Knowledge of Terraform, Looker, or Looker Studio for infrastructure automation and reporting dashboards.
Preferred Certifications
- Google Cloud Professional Machine Learning Engineer
- Google Cloud Associate Cloud Engineer or Professional Cloud Developer
- Google Cloud Generative AI Leader (good to have)
“All qualified applicants will be considered without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or protected veteran status.”
Skills
- Machine Learning
- Generative AI
- GCP
- Gemini
- Vertex AI
- Retrieval-Augmented Generation
- Embeddings
- Cloud Run
- Kubernetes
- GKE
- Apigee
- Cloud Build
- BigQuery
- Google Cloud Storage
- Pub/Sub
- Dataflow
- IAM
- Python
- FastAPI
- Flask
- pytest
- Vector Databases
- pgvector
- LLM
- LangChain
- LangGraph
- Cloud Functions
- Git
- Docker
- OCR
- Model Context Protocol
- Terraform
- Looker
- Looker Studio
More jobs at Datum Software
All 61Similar roles
- Data BI AnalystINSPYR Solutions · Nashville, TN · USD 48–50/hrjust now
- Senior Data Engineer, Microsoft Fabric & AnalyticsMitchell Martin · Greenwich, CTtoday
- Senior Data Engineer - HybridGenesis10 · Jersey City, NJ · USD 58–66/hrtoday
- Senior Data ScientistCelestar · Washington, DC · USD 175,000–180,000today
- Architect / Data Engineer - HybridGenesis10 · Chandler, AZ · USD 60–68/hrtoday
- Data AnalystGenesis10 · Pennington, NJ - Jersey City, NJ · USD 60–68/hrtoday