Senior Staff Agentic AI Engineer

Bread Financial; Columbus (OH); Hybrid; USD 155,600 - 333,300; Full time

Job summary

Bread Financial is seeking a Senior Staff Software Engineer – Agentic AI to design and deliver core agent capabilities, including policy execution, reasoning, orchestration, and failure handling. You will build production-ready agent runtimes, memory systems, planners, and tool-routing components with strong observability and evaluation pipelines.

You will mentor peers, lead safety and compliance standards, and collaborate with Product to shape AI strategy while ensuring real-time data access

Qualifications

• Bachelor's Degree in Computer Science or related field required.
• 12+ years of Software Engineering experience, incl. 2+ years in AI/ML/LLMs or agent-based systems.
• 3+ years of IaC (Terraform or Ansible).

Responsibilities

• Design and enhance multi-agent frameworks and LLM-powered autonomous systems.
• Implement and refine ReAct, CoT, and ToT reasoning loops across workflows.
• Measure and improve agent decision reliability with telemetry and guardrails.
• Architect safety controls using Policy Enforcement Points.
• Operate and scale production agentic AI platforms on Kubernetes.
• Establish enterprise safety guardrails and compliance for high-risk workflows.
• Partner with Product to shape AI strategy and real-time data access.
• Communicate complex agentic concepts to non-technical stakeholders.

Skills

Agent Based Modeling

AWS

Datadog

OpenAI

Grafana

Graph Databases

Large Language Models

PostgreSQL

Prometheus

New Relic

Redis

Telemetry

Education

Bachelor's Degree in Computer Science or related field

Master’s Degree (preferred)

Tools

Terraform

Ansible

Job description

Job Summary

Senior Staff Software Engineer – Agentic AI will design and deliver core agent capabilities, including policy execution, reasoning, orchestration, and failure‑handling. They will build production‑ready agent runtimes—state and memory systems, planners, and tool‑routing components—while ensuring safety, reliability, latency, and cost efficiency. The role will contribute to multi‑agent workflows for classification, routing, reconciliation, anomaly detection, and decisioning, integrating deterministic paths, graph/RAG memory, and establishing strong observability and evaluation pipelines. The engineer will mentor peers and uphold high engineering standards across the team.

Essential Job Functions

• Design and enhance multi‑agent frameworks and LLM‑powered autonomous systems using goal schemas, planner‑executor patterns, and well‑defined policy enforcement points. Contribute to the definition and implementation of agent state and memory architectures with PII‑minimization practices and TTL strategies. (20%)
• Implement and refine ReAct, CoT, and ToT reasoning loops, standardize their use across agent workflows, build evaluation signals using curated golden datasets, and contribute to agent‑to‑agent communication protocols (15%)
• Measure and improve agent decision reliability using tools such as LangSmith, Arize Phoenix, Weights & Biases. Design deterministic tool‑chaining patterns, safeguards, grounding techniques, and integrate accounting for reliable behavior. (15%)
• Architect and implement safety controls such as scoped tool access, validators, red‑team hooks, and human‑escalation paths, using AgentSpec to define Policy Enforcement Points that prevent high‑risk or irreversible actions. (15%)
• Operate and scale production agentic AI platforms on Kubernetes, define agent‑centric SLOs, instrument deep telemetry, and support on‑call through agent‑assisted triage, automated rollback/roll‑forward, and human‑gated controls. (15%)
• Establish enterprise safety guardrails, ethical guidelines, and compliance standards to ensure agents operate within legal, regulatory, and organizational boundaries, especially in high‑risk or financial workflows. (10%)
• Partner with Product to shape AI strategy and user experiences, ensuring agents access high‑quality real‑time data across SQL systems, CRMs, SaaS platforms, APIs, and event streams. (5%)
• Communicate complex agentic concepts—such as CoT, RAG, and safety controls—to non‑technical stakeholders, promote AI‑native engineering practices, and model resilience around model failures. (5%)

Minimum Qualifications

• Bachelor’s Degree in Computer Science or related field.
• 12+ years of Software Engineering experience, including 2+ years in AI/ML, LLMs, agent‑based systems or large‑scale distributed systems, and 3+ years of IaC (Terraform or Ansible).

Preferred Qualifications

• Master’s Degree in Computer Science or related field.
• 15+ years of Software Engineering experience, including 3+ years in AI/ML, Generative AI, or agentic systems, 4+ years of fintech/payments integration, PCI and data protection familiarity, and 4+ years of IaC (Terraform or Ansible).

Skills

• Agent Based Modeling
• AWS
• Datadog
• OpenAI
• Grafana
• Graph Databases
• Large Language Models (LLMs)
• PostgreSQL
• Prometheus
• New Relic
• Redis
• Telemetry

Reports To

Director and above

Work Environment

Normal office environment. Remote or hybrid, with 3–4 days per month required in office for locations within 60 miles of a Bread Financial site. On‑call rotation includes evenings or weekends.

Physical and Mental Requirements

Must be able to comply with essential functions: communicate, hear, talk, type and write.

Salary Range

$155,600.00 – $333,300.00

Equal Opportunity & EEO Statement

• The Company is an Equal Opportunity Employer.
• Applicants must be legally authorized to work in the United States.
• The Company participates in E‑Verify and will consider all qualified applicants, including those with a criminal history.
• The Company complies with the Americans with Disabilities Act and provides reasonable accommodations.