Principal Software Engineer

Kadencetalent — United States · Posted ~3 days ago

Lead Full-time Hybrid

Skills

Python FastAPI LLMs Generative AI Agentic AI PostgreSQL AWS Distributed Systems API Design Vector Databases RAG Semantic Search Embeddings MCP

🔓 Log in to save this job, tailor your resume & track your apply process — 7 days free, no card needed.

Log in to add to target list

Summary

Lead the design of production-grade AI platforms, architect secure and scalable backend systems, build advanced retrieval pipelines, and mentor engineering teams delivering enterprise software.

Highlights

Lead architecture for enterprise-scale AI systems, influence technical strategy, mentor engineers, and work in a flexible hybrid environment with strong career growth opportunities.

Description

Principal Software Engineer – Generative & Agentic AI Location: Hybrid opportunities in New York, NY; Dallas/Frisco, TX; Minneapolis/Eagan, MN; Ann Arbor, MI; and Toronto, ON Employment Type: Full-Time The Opportunity We are hiring a Principal Software Engineer to help shape the technical foundation behind a large-scale, AI-powered platform used by professionals to perform complex, high-stakes work. This is a senior technical leadership role focused on building production-grade generative AI and agentic systems, including the backend services, orchestration layers, retrieval infrastructure, and access controls required to deploy AI reliably at enterprise scale. You’ll work alongside experienced engineers, AI/ML specialists, researchers, and product leaders to turn advances in LLMs and agentic AI into secure, scalable products used by a large global customer base. What You’ll Do Set technical direction for backend and AI platform architecture, establishing patterns for LLM applications, AI agents, MCP servers, tool use, retrieval, and orchestration.Design and build production systems that support high volumes of complex data and concurrent AI interactions, balancing performance, reliability, security, and cloud infrastructure costs.Lead complex engineering initiatives from early architecture and experimentation through production rollout and long-term operation.Build infrastructure for sophisticated agentic workflows, including multi-step reasoning, tool calling, model integrations, and orchestration across third-party and internally developed AI systems.Partner closely with AI/ML engineers and researchers to evaluate emerging model capabilities and translate them into dependable, customer-facing product experiences.Design scalable retrieval and data systems involving large document collections, semantic search, embeddings, vector databases, indexing, and custom retrieval pipelines.Establish engineering practices for testing and evaluating AI systems where outputs may be non-deterministic, with a strong focus on reliability, observability, and safe deployment.Architect secure identity and access patterns for AI-powered applications, including authentication, authorization, scoped permissions, service identities, and entitlement management.Collaborate across engineering, product, security, infrastructure, and compliance teams to ensure systems meet demanding standards around data protection, isolation, auditing, and access control.Mentor senior engineers and influence engineering standards across architecture, code quality, system design, AI integration, and operational excellence. What We’re Looking For Significant experience designing and building complex, production-grade software systems at scale.Hands-on experience developing applications powered by LLMs, generative AI, agents, and/or retrieval systems.Deep expertise with Python and modern backend development frameworks such as FastAPI or similar technologies.Strong experience with relational databases such as PostgreSQL and production infrastructure on a major cloud platform, ideally AWS.A strong foundation in distributed systems, including API design, data modeling, scalability, observability, resilience, and performance optimization.Experience taking technically complex projects from architecture and design through execution, launch, and ongoing production ownership.Strong technical communication skills and the ability to influence architecture and engineering decisions across multiple teams. Bonus Experience Building and operating agentic AI systems in production, including multi-step workflows, tool calling, MCP, and agent orchestration.Integrating and operating frontier LLMs from providers such as OpenAI, Anthropic, or similar model platforms.Designing infrastructure around embeddings, vector databases, semantic search, RAG, and advanced retrieval pipelines.Developing evaluation, automated testing, monitoring, and release strategies specifically for AI-powered applications.Experience balancing model performance, latency, infrastructure costs, reliability, and safety in production AI systems. Why Join? This is an opportunity to work on a flagship AI platform with significant investment and executive visibility, tackling some of the most challenging problems at the intersection of generative AI, agentic systems, search, retrieval, security, and enterprise software. You’ll have the ability to influence technical strategy beyond a single product or feature, working with a highly experienced team while building AI systems designed for real-world, high-stakes professional use. The organization offers a flexible hybrid working environment, comprehensive benefits, professional development opportunities, flexible time off, and programs designed to support long-term career growth and work-life balance.