Staff Software Engineer - AI Applications
Leads development of AI-powered fintech applications, building scalable backend services, frontend experiences, and GenAI features like agent orchestration and RAG for customer support and integrations. Requires hands-on LLM experience, full-stack skills, and ability to experiment rapidly with user feedback.
About the job
Responsibilities
- Build across the stack: design, develop, and maintain scalable backend services and APIs, as well as intuitive, high-quality frontend applications.
- Work with AI engineers, software engineers, and machine learning engineers to architect, design, and implement GenAI-powered products and features.
- Collaborate across functions to understand user needs and propose/implement AI-powered solutions with highest impact.
- Design and execute rapid experiments to push boundaries on business impact from emerging AI capabilities, focusing on minimal viable testing.
- Balance creative exploration with rigorous evaluation of technical feasibility, product potential, and business impact.
Requirements
- Experience building backend services and working with microservices or service-oriented architectures.
- Strong working knowledge of HTML, CSS, JavaScript, and modern frontend frameworks or libraries.
- Hands-on experience working with LLMs to build and ship products, iterating with real user feedback, including:
- Prompt engineering
- Fine-tuning
- Retrieval augmented generation (RAG)
- Semantic search - vector database and embedding models
- Agent orchestration frameworks
- Evaluation and monitoring frameworks for open-ended tasks
- Streaming and SSE
- Common UX and design patterns for GenAI-powered products
- Strong debugging and monitoring experience for production systems.
- Ability to deeply understand customer/user needs through user research and rapid experimentation.
- Ability to balance divergent and convergent thinking for 0→1 projects.
- Extremely curious and passionate about GenAI applications.
Nice-to-Haves
- Experience training/serving ML models in production, or fine-tuning LLMs for domain-specific use cases.
- Comfortable operating in privacy/PII-sensitive environments with compliance mitigations.
Skills
JavaScript, HTML, CSS, LLMs, Prompt Engineering, Fine-Tuning, RAG, Semantic Search, Vector Databases, Embedding Models, Agent Orchestration, Microservices, Generative AI, Streaming, Sse
Similar jobs
Fullstack Engineering jobs
Suno
Cambridge, MABuild and own Songkick’s systems across backend, mobile, data, and notifications while leading its technical integration with Suno. The role requires 5+ years of hands-on software engineering experience, strong API and architecture skills, and comfort in ambiguous startup environments.
Harvey
San Francisco, CALeads cross-team product engineering initiatives spanning full-stack, backend, and AI systems, including agentic capabilities, secure retrieval infrastructure, and customer-facing applications. Requires 10+ years of software engineering experience, Staff-level scope, and strong React, TypeScript, Python, and scalable systems expertise.
Prompt Health
United States
Staff-level individual contributor leading architecture, technical strategy, and execution for complex enterprise web applications. The role requires deep full-stack experience, strong data architecture and query-performance expertise, hands-on coding, and the ability to mentor engineers.
Chime
New York, NYLeads the architecture and hands-on development of LLM-powered financial assistant capabilities, including agent systems, evaluations, guardrails, and scalable backend services. Requires 8+ years of backend or full-stack experience, strong distributed-systems expertise, and production experience shipping AI features.
Shield AI
San Mateo, CA
Leads development, integration, validation, and field deployment of autonomy software for unmanned platforms. Requires senior-level C++ and Linux experience, embedded and real-time systems expertise, technical leadership, and mission-test support.