bolt.new · 10 hours ago
Staff Applied AI Engineer
United States
Full-time
Remote
Lead/StaffStackBlitz is a company focused on creating innovative development tools, and they are seeking a Staff Applied AI Engineer to lead the technical direction of AI agents that transform natural language into production-ready applications. The role involves defining AI agent architectures, driving multi-provider strategies, and collaborating across teams to align AI initiatives with business objectives.
Developer PlatformInformation TechnologySoftware
Responsibilities
Define AI Agent Architecture: Lead the design and evolution of our AI agent systems, establishing patterns, frameworks, and standards that teams across the organization adopt. Own the technical vision for how agents manage context, orchestrate workflows, and scale to handle increasingly complex user needs
Drive Multi-Provider Strategy: Shape our approach to leveraging models from providers such as OpenAI (GPT series), Anthropic (Claude), and Google (Gemini). Establish evaluation frameworks and selection criteria that teams use to choose the right model for a given task. Build relationships with provider teams to influence roadmaps and beta-test new capabilities
Architect Tool Use and Workflow Systems: Design the foundational systems that enable AI agents to call external tools and APIs safely and effectively. Define the abstractions and interfaces that allow the agent to perform actions like web searches, database queries, and domain-specific operations. Evaluate and recommend frameworks such as Vercel's AI SDK, LangGraph, and others, establishing best practices for the organization
Cross-Team Leadership: Partner with teams across engineering, product, and design to align AI initiatives with business objectives. Influence roadmaps, resolve technical disagreements, and ensure AI-driven features are architected for long-term maintainability and performance. Mentor senior and mid-level engineers, raising the bar for AI engineering practices across the organization
Establish Data and Evaluation Standards: Define the methodology for collecting, curating, and analyzing datasets from agent responses and multi-turn conversations. Build and steward the evaluation harness, ensuring evals directly support business objectives and KPIs. Turn insights from conversation patterns, failure modes, and success signals into systematic improvements
Drive Research and Innovation: Stay at the forefront of NLP and LLM research, identifying and championing novel techniques that provide competitive advantage. Lead experimentation with new prompting strategies, context handling methods, and fine-tuning opportunities. Represent StackBlitz in external forums, conferences, and community discussions where appropriate
Qualification
Required
Familiarity with TypeScript is important. Our entire stack is built on it. Willingness to work in TS daily is key
Extensive hands-on experience working with Large Language Models (LLMs), with a nuanced understanding of their capabilities, limitations, and emergent behaviors. Proven track record of building and scaling production AI systems
Deep expertise in prompt engineering with the ability to establish best practices and mentor others. Skilled at crafting, refining, and optimizing prompts across different tasks, models, and use cases
Strong software engineering fundamentals with experience designing systems that scale. Able to make architectural decisions that balance immediate needs with long-term maintainability
Ability to take ambiguous, high-scope problems and drive them to completion with minimal oversight. Comfortable influencing direction across teams and navigating complex technical and organizational challenges
Ability to identify process, communication, and technical debt across the organization and propose solutions that accelerate velocity for multiple teams
Experienced in establishing data collection and analysis practices. Able to build evaluation frameworks, identify patterns in agent behavior, and translate findings into organizational improvements
Strong verbal and written English communication skills are required, as this role involves frequent collaboration with team members, stakeholders, customers, and potentially external audiences where English is the primary working language
Preferred
Familiarity with DSPy (Declarative Self-improving Python) for building modular AI systems and optimizing prompts programmatically
Understanding of ML fundamentals and experience with model evaluation metrics
Experience contributing to or maintaining open-source AI/ML projects
Experience reading and implementing techniques from AI/ML research papers
$ Experience speaking at conferences, publishing technical content, or representing an organization in industry forums
Company
bolt.new
Build stunning apps & websites by chatting with ai.
Founded in 2018
11-50 employees
Funding
Current Stage
Growth StageTotal Funding
$113.4M2025-01-22Series B· $105.5M
2022-04-06Seed· $7.9M
Leadership Team
Eric Simons
CEO & Founder
Recent News
2025-10-10
2025-08-14
Company data provided by crunchbase