Full Stack Agentic Developer

About the job

Responsibilities

• Build and evolve the React web application across core product surfaces like authentication, session setup, workspace navigation, file review, streaming agent activity, results review, and user-facing administration.
• Create reusable component patterns for complex, stateful workflows, ensuring maintainability, accessibility, and extensibility.
• Build and maintain Express/TypeScript API endpoints for session orchestration, file management, workspace operations, usage tracking, and new product capabilities.
• Integrate frontend workflows with backend services for authentication, LLM routing, usage tracking, agent orchestration, cloud storage, and PostgreSQL data.
• Translate complex backend and agent states into intuitive interface patterns, including empty states, progress states, error states, review states, and resumable workflows.
• Implement and improve real-time streaming interfaces between the backend, agent runtime, and UI using server-sent events and event-driven patterns.
• Render incremental agent output such as token-by-token text, tool execution cards, plans, task lists, progress indicators, cost and usage indicators, file changes, warnings, and final workflow states.
• Manage stream connection lifecycle, retries, cancellation, cooperative stop, stop/resume behavior, error recovery, and provide clear feedback for long-running agent workflows.
• Define event contracts for clear presentation of agent behavior in the UI without exposing unnecessary implementation complexity.
• Design UX and API patterns to help users understand agent actions, file changes, reviewable outputs, and areas requiring human judgment.
• Own and improve parts of the custom multi-turn agent loop, including model provider communication, response parsing, tool execution, result observation, and iteration within isolated cloud containers.
• Develop proprietary tools to expand agent capabilities in file operations, analysis, transformation, visualization, document creation, data processing, validation, and workflow automation.
• Extend the containerized execution environment to support new languages, libraries, utilities, file types, analytical methods, and integrations.
• Design clear tool schemas, permission boundaries, workspace access patterns, input validation, and error messages for effective and safe tool usage by agents.
• Create reusable patterns for adding new tools to expand agent capabilities without compromising runtime stability, transparency, or debuggability.
• Support multi-model integration across OpenAI, Anthropic, and other frontier or local models, handling provider-specific formats, tool-calling, streaming, structured outputs, and errors.
• Build and maintain translation layers to normalize provider differences while preserving access to model capabilities.
• Design and maintain prompt and context systems to shape agent behavior, including analytical identity, methodology compliance, interaction modes, tool usage policies, quality standards, and escalation patterns.
• Implement token estimation, usage tracking, context compression, and conversation summarization.

Requirements

• Strong product and platform skills with experience in LLM-powered agentic systems.
• Proficiency in designing excellent product experiences.
• Production-grade TypeScript and React development skills.
• Experience extending Node.js/Express APIs.
• Understanding of how agentic systems plan, use tools, recover from errors, stream activity, and produce inspectable, trustworthy work.
• Experience with real-time streaming interfaces, primarily server-sent events and related event-driven patterns.
• Familiarity with managing stream connection lifecycles, retries, cancellation, and error recovery.
• Experience designing UX and API patterns for agent behavior visualization.
• Experience with multi-turn agent loops, including model provider interactions, response parsing, tool execution, and iteration.
• Experience developing tools for agents across various functions like file operations, analysis, and data processing.
• Experience extending containerized execution environments.
• Experience designing tool schemas, permission boundaries, and input validation for agents.
• Experience supporting multi-model integration across different LLM providers (e.g., OpenAI, Anthropic).
• Experience building and maintaining translation layers for LLM provider normalization.
• Experience designing and maintaining prompt and context systems for shaping agent behavior.
• Experience implementing token estimation, usage tracking, context compression, and conversation summarization.