Staff AI Platform Engineer

Job Summary

The Lead Data Platform Agentic AI Engineer will design and build core platform capabilities that enable secure, scalable GenAI and Agentic AI solutions across Bread Financial. This role will develop foundational services such as, agent orchestration, vector search, LLM interfaces, and observability and security frameworks that allow product teams to deliver reliable AI features quickly and safely. The Lead Engineer will work closely with platform, security, and application teams, ensuring AI platform components are production-ready, well-governed, and aligned to enterprise standards. The Lead Engineer will apply strong technical judgement, contribute to platform design decisions, and help evolve shared AI infrastructure that accelerates innovation while maintaining trust, reliability, and compliance.

Essential Job Functions

• Design and build orchestration layers for LLM workflows and multi-step agent pipelines (tool use, retrieval, grounding, function calling), with clear SLAs, retries, rate limiting, and tracing. - (20%)
• Implement vector data infrastructure (e.g. Chroma, OpenSearch) including indexing strategies, embeddings management, RAG patterns, and data lifecycle controls. - (15%)
• Develop LLM interfaces & SDKs that abstract providers (Bedrock, Azure/OpenAI, etc.), standardize prompts, enable guardrails, and support evaluation harnesses and A/B testing. - (15%)
• Integrate logging, tracing (e.g., OpenTelemetry), metrics, prompt/response analytics, eval pipelines (quality, toxicity, hallucination), and SLO dashboards. - (10%)
• Enforce data classification, redaction, PII controls, prompt injection defenses, content filtering, secrets management, and policy-as-code for model/endpoint access. - (10%)
• IaC (Terraform/CDK), CI/CD for model and prompt artifacts, environment promotion, and cost monitoring/optimization. - (10%)
• Partner with cross-functional teams (data engineering, security, product) to productionize new capabilities and drive platform adoption through documentation, templates, and enablement. - (10%)
• Participate in on-call rotations, root-cause analysis, and continuous improvement of performance, reliability, and developer experience. - (10%)

Minimum Qualifications

• Bachelor s Degree in Computer Science, Engineering, or related field of study or equivalent, relevant work experience
• 8+ years of overall software engineering experience.
• 3+ years of experience building AI platform components.
• 4+ years of experience implementing LLM-based services: prompt templates, tool/function calling, retrieval-augmented generation, and rate/latency management.

Preferred Qualifications

• Master s Degree in Computer Science, Engineering, or related field of study or equivalent, relevant work experience
• AWS Cloud Practitioner Certification.
• 8+ years of software engineering experience.
• 4+ years of experience building AI platform components.

Skills

• Amazon Aurora
• AWS Cloud Computing
• AWS Elastic Kubernetes Service (EKS)
• AWS Key Management Service (KMS)
• HashiCorp Vault
• GitHub Actions
• Prometheus (Software)
• Python (Programming Language)
• OpenSearch (Software)
• Telemetry
• Terraform
• TypeScript

Reports To

Manager and above

Direct Reports

0

Work Environment

• Normal office environment. Hybrid, 6-8 days per month are required in office.

Other Duties

This job description is illustrative of the types of duties typically performed by this job. It is not intended to be an exhaustive listing of each and every essential function of the job. Because job content may change from time to time, the Company reserves the right to add and/or delete essential functions from this job at any time.

Job Family

Data and Analytics

Job Type

Regular

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.