Senior Software Developer, AI Data Engineer

What you'll be doing:

Design and implement reliable, scalable data ingestion and integration pipelines for structured, semi-structured, unstructured, and multi-modal data (e.g., databases, documents, APIs, events), ensuring data is AI-ready, governed, secure, and observable.

Build and scale retrieval infrastructure, including vector storage, embedding pipelines, hybrid search, and graph-based knowledge representations, while optimizing data modeling for retrieval quality.

Develop and operate agent memory systems and pipelines for AI system signals (tracing, feedback, evaluation, and usage data) to support observability and continuous improvement.

Apply data quality, validation, monitoring, and testing frameworks in production pipelines, ensuring governance, access control, lineage, and security standards are met, including safe handling of sensitive data in AI retrieval and generation workflows.

Monitor, troubleshoot, and optimize AI data pipelines and retrieval workflows for reliability, performance, and cost, with strong observability and resilient processing patterns.

Design and support evaluation workflows for AI systems, enabling offline testing, benchmarking, and continuous improvement of retrieval and agent performance over time.

Lead pragmatic platform evolution by defining clear contracts between AI services and data systems, reducing coupling, and improving developer experience.

What you’ll bring:

Strong software engineering fundamentals, including designing maintainable, testable systems and owning features end-to-end.

Production experience with distributed systems, including async workflows, failure modes, retries, and eventual consistency.

Hands-on experience building and operating data pipelines for AI systems, such as embeddings pipelines, retrieval workflows, or feedback data processing.

Experience working with AI-related data infrastructure, including vector databases, search systems, or graph-based storage.

Experience with retrieval systems (RAG), embedding pipelines, or hybrid search (vector + keyword).

Experience with agent frameworks, agent memory systems, or orchestration of tool-using AI systems.

Experience operating production systems, including monitoring, incident response, and continuous improvement.

Cloud experience on AWS building production systems, including storage, messaging, and orchestration.

Experience with infrastructure as code, with CDK preferred and CloudFormation or Terraform acceptable.

Strong collaboration and communication skills, with the ability to mentor and raise engineering maturity through reviews and design discussions.

Strong English language communication and collaboration skills.

The Tech Stack You’ll Work With:

Backend & Platform: TypeScript, NestJS, Python

Cloud & Infrastructure: AWS EKS, AWS Lambda, AWS Bedrock, AWS AgentCore

Search & Retrieval: AWS OpenSearch Serverless, AWS S3 Vectors, AWS Knowledge Bases

Document & Data Processing: AWS Textract, DynamoDB, S3

AI Evaluation & Observability: LangFuse, LangSmith (or equivalent)

AI-assisted development tools: GitHub Copilot

Developer Tooling: GitHub, GitHub Actions, Nx Monorepo

Collaboration: Jira, Confluence, Microsoft Teams, Outlook

Why this role exists

Caseware is evolving Caseware Cloud to deliver intelligent, data-driven experiences—powering analytics, automation, and AI/agentic capabilities on top of a modern data platform.

This role is for someone who can bridge transactional backend systems and data-intensive distributed workflows . You’ll work on systems that combine:

APIs and domain services (microservices, relational modeling, service boundaries)

Asynchronous workflows (messaging, retries, idempotency, replay safety)

Distributed/batch data processing (Spark-based processing and lake patterns)

Cloud platform primitives (AWS orchestration and managed services)

AI-ready retrieval workflows (embedding + vector retrieval pipelines)

What success looks like (first 6–12 months)

Improved reliability and operability of ingestion + async workflows (clearer idempotency/replay patterns, fewer recurring incidents).

Cleaner boundaries between orchestration/control-plane concerns and data-processing execution concerns.

Better observability across APIs, queues, workflows, and distributed jobs.

Clearer data contracts and more predictable schema evolution practices.

Tangible improvements in developer experience (local run, testing, reduced “environment-only” hacks).

Perks & Benefits

¨Contrato a termino Indefinido¨ with all the legal benefits

Prepaid Medicine

Life insurance and funeral assistance

Internet allowance

Home office stipend

Competitive compensation — above the market average

100% remote work environment and an excellent work-life balance

Opportunity to work for a growing global SaaS leader company

A culture that promotes independence, innovation, trust, and accountability

Open space to be creative, innovative and strategize for the future

Mentorship by highly experienced professional

Budget for training, we want you to grow

5 Personal Time Off days per year

Sick Leave Top up to total 100% of salary paid by the employer from Day 3 to 90.

Recognition Award, additional paid time off in recognition of the corresponding year of service

Upgrade vacation starting at 5 years of service

AI-first environment: Be part of an AI-first engineering organization that embraces modern tools, automation, and AI-driven ways of working.