Senior Software Engineer

As a Senior Software Engineer with AI-native development experience, you will design, build, and operate next-generation AI-powered applications and platforms. You will combine strong full-stack software engineering fundamentals with hands-on expertise in modern AI/ML technologies to build production-grade experiences powered by LLMs, agents, retrieval, and intelligent automation. You will work across the technology stack—from user experiences and APIs to distributed services, data and retrieval systems, AI/ML workflows, and cloud infrastructure. You will be expected to use AI-native development practices to accelerate engineering productivity while maintaining high standards for scalability, reliability, security, and quality. This role is ideal for an engineer who enjoys solving complex problems end-to-end and is excited about applying AI as a core engineering capability, not simply as an add-on to traditional software.

Responsibilities:

• Design and build end-to-end full-stack applications, including frontend experiences, backend services, APIs, data layers, and cloud-native infrastructure.
• Build production-grade AI/ML-powered capabilities using LLMs, RAG, embeddings, semantic search, agentic workflows, and intelligent decision-making.
• Design and implement agentic architectures, including tool calling, orchestration, planning loops, memory, context management, and failure recovery.
• Develop reliable AI-powered APIs and services that integrate frontier models and enterprise data securely and efficiently.
• Build retrieval and grounding pipelines using vector search, hybrid search, semantic retrieval, re-ranking, and contextual enrichment.
• Establish evaluation and observability mechanisms to measure AI quality, accuracy, latency, cost, reliability, and safety.
• Take features from concept and prototype through production deployment and ongoing operation, with ownership of quality and reliability.
• Work with product, design, platform, data, security, and other engineering teams to translate ambiguous problems into scalable technical solutions.
• Contribute to architecture and design decisions, code reviews, engineering standards, and technical direction.
• Mentor engineers and help raise the bar on full-stack engineering and production AI development practices.
• Design and develop scalable, maintainable frontend applications and backend services using REST/GraphQL APIs, microservices, event-driven services, and distributed systems.
• Work with modern frontend technologies such as React, TypeScript, JavaScript, or equivalent frameworks.
• Build cloud-native applications with a strong focus on scalability, performance, reliability, and security.
• Own software delivery across development, testing, deployment, monitoring, and production operations.
• Build applications leveraging LLMs, generative AI, embeddings, RAG, semantic search, and agentic workflows.
• Integrate frontier AI models and SDKs such as OpenAI, Anthropic, Google, or equivalent platforms.
• Apply prompt engineering, structured outputs, function/tool calling, context engineering, and model selection to real-world applications.
• Design agent workflows that can reason, use tools, retrieve information, execute actions, and recover from failures.
• Build AI evaluation frameworks and automated tests to measure model and application quality.
• Balance model capability, accuracy, latency, scalability, and cost when selecting and integrating AI models.
• Apply AI safety, security, privacy, governance, and guardrail practices to production AI systems.
• Explore and adopt emerging AI technologies and rapidly turn promising capabilities into production-ready solutions.

AI-Native Engineering Practices:

• Use AI-assisted development tools and coding agents such as Claude Code, Codex, Cursor, Windsurf, or equivalent tools as part of the software development lifecycle.
• Apply AI to improve engineering productivity across coding, testing, debugging, documentation, code review, and system design.
• Develop effective workflows for collaborating with coding agents while maintaining engineering quality and accountability.
• Help establish best practices for AI-native software development across the engineering organization.

Requirements:

• 5+ years of software engineering experience, or equivalent practical experience.
• Experience designing and delivering production software systems.
• Experience building or integrating AI/ML-powered applications in a production or near-production environment.
• Modern AI experience: LLMs, RAG, embeddings, vector search, agentic workflows, model evaluation, or AI observability.
• Strong programming experience in Python and/or Java, Go, or a similar language.
• Cloud-native technologies, distributed systems, APIs, databases, and scalable architectures.
• Bachelor's or master's degree in computer science, artificial intelligence, machine learning, or a related technical discipline, or equivalent practical experience.
• Cybersecurity or security-product experience is a plus.
• Strong understanding of software engineering fundamentals, data structures, algorithms, design patterns, APIs, and distributed systems.
• Hands-on experience developing full-stack applications, with strength in both frontend and backend engineering.
• Strong programming experience in one or more of Python, Java, Go, TypeScript, JavaScript, or similar languages.
• Experience with modern frontend development, preferably React and TypeScript or equivalent technologies.
• Experience designing and building cloud-native applications, scalable APIs, microservices, databases, and distributed systems.
• Hands-on experience building or integrating AI/ML-powered applications in production or near-production environments.
• Practical understanding of modern AI concepts, including LLMs, embeddings, RAG, vector databases/search, semantic search, agents, tool calling, and model evaluation.
• Experience integrating one or more frontier AI model platforms/SDKs such as OpenAI, Anthropic, or Google.
• Ability to take an AI/ML prototype and turn it into a reliable, scalable, maintainable production solution.
• Strong debugging, problem-solving, and system-design skills.
• Strong communication and collaboration skills with the ability to work effectively across engineering, product, design, data, and platform teams.
• Demonstrated ownership of technical decisions and a track record of improving code quality and engineering practices.

Nice to Have:

• Experience designing multi-agent systems and agent orchestration frameworks.
• Experience with AI evaluation, observability, guardrails, and responsible AI practices.
• Experience with vector databases, hybrid retrieval, re-ranking, knowledge graphs, or enterprise search.
• Experience with ML pipelines, MLOps, model monitoring, or inference optimization.
• Experience with cloud platforms such as AWS, Azure, or GCP.
• Experience with Kubernetes, containers, CI/CD, and infrastructure-as-code.
• Experience with AI coding agents such as Claude Code, Codex, Cursor, or Windsurf.
• Contributions to open-source AI/ML or developer tooling projects.
• Experience working on cybersecurity, identity, risk, enterprise SaaS, or other complex domain platforms is a plus.

What Success Looks Like:

• In this role, you will be successful when you can:
• Build end-to-end: Take a product requirement from UI and API design through AI services, data, deployment, and production operations.
• Build AI-native: Understand when and how to apply LLMs, agents, retrieval, and other AI capabilities to solve problems effectively.
• Engineer for production: Move beyond prototypes and deliver systems that are scalable, observable, secure, reliable, and maintainable.
• Think across the stack: Understand the trade-offs between user experience, application architecture, data, AI models, infrastructure, cost, and performance.
• Raise the engineering bar: Influence architecture, mentor engineers, and establish effective practices for building AI-native software.