Interface AI
Staff Software Engineer - Backend Core AI
Interface AI, San Jose, California, United States, 95199
Overview
interface.ai is the industry's-leading specialized AI provider for banks and credit unions, serving over 100 financial institutions. The company's integrated AI platform offers a unified banking experience through voice, chat, and employee-assisting solutions, enhanced by cutting-edge proprietary Generative AI. Our mission is to transform the banking experience so every consumer enjoys hyper-personalized, secure, and seamless interactions, while improving operational efficiencies and driving revenue growth. interface.ai offers pre-trained, domain-specific AI solutions that are easy to integrate, scale, and manage, both in-branch and online. Combining this with deep industry expertise, interface.ai is the AI solution for banks and credit unions that want to deliver exceptional experiences and stay at the forefront of AI innovation.
What You’ll Do
Lead Design and Implementation of Advanced Routing: Architect and implement hierarchical and plan-based routing systems for autonomous agents with latency targets of 800–1500 ms to ensure responsive user interactions.
Build Secure PII Pipelines: Develop PII masking and transactional guardrails, design secure data flows, and enforce idempotency and transaction safety across external tool calls.
Own Model Selection and Inference Strategy: Drive strategic selection and optimization of inference models, integrating large language models and fine-tuned or custom small models, and leverage high-performance inference engines to maximize throughput and minimize latency.
Design Efficient Memory Layers: Architect memory layers including short-term rolling windows, retrieval memory, and audited long-term state management to minimize token usage and optimize resources.
Ship Comprehensive Observability: Implement observability for agent behavior, including per-turn token and latency budgeting, attribution, and red-flag alerting for anomalies or performance degradation.
Stand Up Evals & Reinforcement Learning: Establish evaluation frameworks and auto-evolution loops, including regression suites, reward models for agent behavior optimization, and bandit algorithms for dynamic prompt/model/tool selection.
Mentor and Elevate Standards: Act as a technical mentor, set high standards for code quality, incident response, and change management processes.
What We’re Looking For Required Qualifications
Extensive Distributed Systems Experience: 8+ years designing, building, and maintaining high-throughput, low-latency distributed systems. Proficiency in Go, Rust, Java, C++, or Python.
Proven LLM Agent Deployment: Hands-on experience deploying and tuning multi-agent frameworks and LLM agents, implementing function-calling, or operating production-grade RAG systems at scale.
Deep Streaming and Orchestration Knowledge: Experience with streaming technologies (e.g., WebRTC/LiveKit, gRPC), asynchronous orchestration, idempotency keys, and exact-once semantics in distributed environments.
Practical Security and Compliance: Strong experience with secure PII handling, key management, audit trails, and policy enforcement in regulated environments.
Strong Optimization Instincts: Proficiency in prompt engineering and token optimization for LLMs to maximize efficiency and reduce costs.
Reinforcement Learning Expertise: Experience with RLHF/RLAIF, reward modeling, online learning techniques (bandit algorithms), and evaluation harnesses for AI models.
Preferred Experience
Voice Systems Experience: Familiarity with STT and TTS latency, and practical experience with telephony or voice quality assurance.
Banking/FinServ Background: Prior experience in banking or financial services with understanding of regulations and compliance standards.
What Makes This Role Special
Define the core AI infrastructure powering autonomous financial workflows across millions of users.
Lead the engineering strategy behind multi-agent AI systems, shaping how autonomous AI thinks and operates.
Compensation
Compensation is expected to be between $210,000 - $240,000. Exact compensation may vary based on skills and location.
What We Offer
Health: medical, dental, and vision insurance with wellbeing resources.
Time away: Public holidays and discretionary PTO with manager approval.
Financial: 401K, ESPP, life and AD&D insurance, long-term and short-term disability.
Family: parental leave.
Development: Access to internal professional development resources.
Interface.ai is committed to an inclusive, diverse, and accessible workplace. We do not discriminate on any protected characteristic. All employment decisions are based on business needs, job requirements, and individual qualifications.
#J-18808-Ljbffr
interface.ai is the industry's-leading specialized AI provider for banks and credit unions, serving over 100 financial institutions. The company's integrated AI platform offers a unified banking experience through voice, chat, and employee-assisting solutions, enhanced by cutting-edge proprietary Generative AI. Our mission is to transform the banking experience so every consumer enjoys hyper-personalized, secure, and seamless interactions, while improving operational efficiencies and driving revenue growth. interface.ai offers pre-trained, domain-specific AI solutions that are easy to integrate, scale, and manage, both in-branch and online. Combining this with deep industry expertise, interface.ai is the AI solution for banks and credit unions that want to deliver exceptional experiences and stay at the forefront of AI innovation.
What You’ll Do
Lead Design and Implementation of Advanced Routing: Architect and implement hierarchical and plan-based routing systems for autonomous agents with latency targets of 800–1500 ms to ensure responsive user interactions.
Build Secure PII Pipelines: Develop PII masking and transactional guardrails, design secure data flows, and enforce idempotency and transaction safety across external tool calls.
Own Model Selection and Inference Strategy: Drive strategic selection and optimization of inference models, integrating large language models and fine-tuned or custom small models, and leverage high-performance inference engines to maximize throughput and minimize latency.
Design Efficient Memory Layers: Architect memory layers including short-term rolling windows, retrieval memory, and audited long-term state management to minimize token usage and optimize resources.
Ship Comprehensive Observability: Implement observability for agent behavior, including per-turn token and latency budgeting, attribution, and red-flag alerting for anomalies or performance degradation.
Stand Up Evals & Reinforcement Learning: Establish evaluation frameworks and auto-evolution loops, including regression suites, reward models for agent behavior optimization, and bandit algorithms for dynamic prompt/model/tool selection.
Mentor and Elevate Standards: Act as a technical mentor, set high standards for code quality, incident response, and change management processes.
What We’re Looking For Required Qualifications
Extensive Distributed Systems Experience: 8+ years designing, building, and maintaining high-throughput, low-latency distributed systems. Proficiency in Go, Rust, Java, C++, or Python.
Proven LLM Agent Deployment: Hands-on experience deploying and tuning multi-agent frameworks and LLM agents, implementing function-calling, or operating production-grade RAG systems at scale.
Deep Streaming and Orchestration Knowledge: Experience with streaming technologies (e.g., WebRTC/LiveKit, gRPC), asynchronous orchestration, idempotency keys, and exact-once semantics in distributed environments.
Practical Security and Compliance: Strong experience with secure PII handling, key management, audit trails, and policy enforcement in regulated environments.
Strong Optimization Instincts: Proficiency in prompt engineering and token optimization for LLMs to maximize efficiency and reduce costs.
Reinforcement Learning Expertise: Experience with RLHF/RLAIF, reward modeling, online learning techniques (bandit algorithms), and evaluation harnesses for AI models.
Preferred Experience
Voice Systems Experience: Familiarity with STT and TTS latency, and practical experience with telephony or voice quality assurance.
Banking/FinServ Background: Prior experience in banking or financial services with understanding of regulations and compliance standards.
What Makes This Role Special
Define the core AI infrastructure powering autonomous financial workflows across millions of users.
Lead the engineering strategy behind multi-agent AI systems, shaping how autonomous AI thinks and operates.
Compensation
Compensation is expected to be between $210,000 - $240,000. Exact compensation may vary based on skills and location.
What We Offer
Health: medical, dental, and vision insurance with wellbeing resources.
Time away: Public holidays and discretionary PTO with manager approval.
Financial: 401K, ESPP, life and AD&D insurance, long-term and short-term disability.
Family: parental leave.
Development: Access to internal professional development resources.
Interface.ai is committed to an inclusive, diverse, and accessible workplace. We do not discriminate on any protected characteristic. All employment decisions are based on business needs, job requirements, and individual qualifications.
#J-18808-Ljbffr