13 hours ago
Responsibilities
- Architect and deliver enterprise-scale Agentic AI voice systems using workflow control, LLM reasoning, tool orchestration, memory management, and secure API integration.
- Build production-grade conversational AI solutions integrating speech-to-text, text-to-speech, LLMs, cognitive services, and backend enterprise systems.
- Design multi-step agentic workflows with planning, function calling, tool routing, state management, and human-in-the-loop escalation.
- Optimize real-time voice systems for latency, reliability, scalability, and cost through streaming architecture, token optimization, semantic caching, and prompt tuning.
- Deploy highly available AI services across Azure and AWS using Kubernetes, containers, serverless services, multi-region resilience, and secure DevOps practices.
- Build evaluation, experimentation, and observability frameworks for conversational quality, routing accuracy, latency, hallucination risk, tool-call reliability, and production performance.
- Implement security, privacy, Responsible AI, and compliance guardrails for sensitive customer data and regulated banking use cases.
- Troubleshoot distributed AI systems involving latency, model behavior, prompt failures, token limits, API errors, orchestration defects, and non-deterministic outcomes.
- Collaborate with product, architecture, engineering, cloud, data, security, and business teams to translate requirements into scalable AI solutions.
- Mentor engineers in AI-first software engineering, automated testing, observability, deployment discipline, and production support.
Requirements
- At least 5 years of backend or platform engineering experience.
- Strong proficiency in Python, Java, C#, or .NET, with foundations in data structures, algorithms, APIs, and distributed systems.
- Hands-on experience building LLM-powered applications, agentic workflows, tool or function calling, state management, retrieval patterns, and multi-step orchestration.
- Practical experience with conversational AI, speech-to-text, text-to-speech, NLP/NLU, real-time voice interactions, or voice assistant platforms.
- Experience moving AI solutions from prototype to production with attention to latency, reliability, scalability, observability, cost efficiency, and resilience.
- Experience evaluating AI systems through prompt testing, response-quality assessment, hallucination analysis, tool-call accuracy, routing performance, A/B testing, and regression validation.
- Experience deploying services on Azure, AWS, or similar platforms using containers, serverless architecture, CI/CD, infrastructure as code, and secure configuration.
- Ability to protect sensitive data and align solutions with privacy, security, Responsible AI, and regulated-industry expectations.
- Strong debugging, root-cause analysis, and production support skills across asynchronous, distributed, and non-deterministic systems.
- Curiosity and ability to evaluate emerging AI frameworks, models, research patterns, and architecture approaches.
- Preferred experience in banking, fintech, regulated industries, contact-center modernization, IVR transformation, CCaaS, or enterprise customer experience systems.
- Preferred advanced degree in Computer Science, Engineering, Artificial Intelligence, or a related field, or equivalent practical experience.
Benefits
- Opportunities to make an impact in fintech.
- Personal and professional learning opportunities.
- Inclusive and diverse work environment.
- Resources to give back to the community.
- Competitive salary and benefits.
Categories
About FIS
FIS builds financial technology for banks, merchants, and capital-markets firms, including core banking platforms, payment processing, fraud/risk tools, and investment/treasury systems. It sells enterprise software, cloud services, and outsourced processing via long-term contracts and transaction-based fees. Founded in 1968 and headquartered in Jacksonville, Florida, FIS is a Fortune 500 public company trading on the NYSE (FIS) with customers worldwide.