Senior Software Engineer - AI Data Migrations & Exchanges

We're a growing SaaS company focused on solving complex data integration and migration challenges for our customers. We're early in our AI journey and that's intentional. Rather than sprinkling AI on top of existing workflows, we're thoughtfully building a secure, governed AI foundation that meaningfully reduces manual effort, accelerates timetovalue, and improves data quality for data engineers and analysts.

This is a unique opportunity to help shape our AI strategy from the ground up and deliver production‑grade AI systems that customers can trust.

As a Senior AI Software Engineer, you will design and build AI‑powered automation that tackles the most time‑consuming aspects of data migration and data exchange, processing, mapping, validation, transformation, reconciliation, and documentation within a highly secure, auditable environment.

You’ll create reliable, production‑ready AI services that integrate deeply into our data pipelines, reduce manual workflows, and enable faster, safer implementations. You’ll work closely with data engineering, platform, and business stakeholders to bring AI capabilities into production while meeting stringent governance, security, and compliance requirements.

This is a hands‑on role for someone who enjoys both building and shaping and developing real systems while helping define best practices, guardrails, and patterns for AI across the company.

• Develop AI agents and workflows to automate schema mapping, transformation rule discovery, code generation (SQL, dbt, Spark), data quality rule authoring, and reconciliation explanations.
• Build AI copilots that assist with impact analysis (e.g., schema changes), field‑level mapping suggestions, and lineage documentation.
• Partner with data engineers and analysts to ensure AI outputs are practical, explainable, and trustworthy.

• Build and ship robust microservices and functions that integrate LLMs (via APIs or on‑prem models) into our data stack.
• Implement observability and reliability patterns including metrics, tracing, logging, caching, retries, rate limits, quotas, and circuit breakers to manage cost, performance, and resilience.
• Design systems with production constraints in mind—not prototypes.

• Develop tools for automated exploratory data analysis, anomaly detection triage, and explainable data quality insights.
• Build safe synthetic and test data generators conditioned on schemas and constraints.
• Implement privacy‑preserving techniques such as PII redaction, tokenization, and masking.

• Enforce strong AI guardrails: prompt hardening, content filtering, policy checks, and intelligent model routing.
• Integrate with secrets management, KMS/HSMs, VPC or private networking, audit logging, and access controls (RBAC/ABAC).
• Collaborate with stakeholders on model risk assessments, data residency, retention, and usage policies.
• Implement deterministic and provable AI flows where required.

• Build automated evaluation pipelines for LLM outputs—covering accuracy, coverage, drift, bias, safety, latency, and cost.
• Introduce human‑in‑the‑loop (HITL) review workflows for business‑critical mappings and transformations.
• Continuously improve system quality through feedback loops and experimentation.

• Document AI capabilities, limitations, and operational playbooks.
• Create reusable prompt libraries, templates, SDKs, and internal tooling.
• Enable data engineers and analysts to effectively use AI features and adopt them into CI/CD workflows.

• 8+ years of experience in software or data engineering, with 2+ years building AI/ML or LLM‑powered systems.
• Strong programming skills in Python (and/or Scala, Java, or Type Script).
• Proven experience delivering production microservices (REST/gRPC) with CI/CD.
• Hands‑on experience with LLM orchestration frameworks and concepts such as Lang Chain, Llama Index, OpenAI SDKs, prompt engineering, RAG, and tool/function calling.
• Experience integrating AI into data platforms and data models.
• Solid knowledge of…