Software Engineer – AI & Autonomous Agents

Company: Autonoms AI
Location: Remote — Austin, TX, US
Employment: Contract
Schedule: Starting at 30 hours/month
Compensation: $20–$30/hour
Role Summary
We are looking for a Software Engineer with strong experience building AI-powered applications and autonomous agents.
This role combines traditional software engineering with modern AI development. You will be responsible for taking business requirements or product ideas, designing technical solutions, building applications, integrating APIs and AI models, and deploying working products.
You will also build AI agents capable of reasoning, using tools, interacting with APIs and external systems, maintaining context, and completing multi-step tasks with limited human intervention.
Key Responsibilities
Software Development
Design, build, test, deploy, and maintain web applications and internal software tools.
Develop frontend and backend applications using JavaScript, TypeScript, Python, React, Next.js, Node.js, FastAPI, or similar technologies.
Build and consume REST APIs and webhooks.
Integrate third-party APIs, SaaS platforms, databases, and internal systems.
Implement authentication, authorization, and appropriate access controls.
Work with databases such as PostgreSQL, Supabase, MongoDB, or similar technologies.
Write clean, maintainable, and well-documented code.
Review, debug, and improve existing codebases.
Use Git and GitHub for source control and development collaboration.
AI and Autonomous Agent Development
Build autonomous and semi-autonomous AI agents capable of completing multi-step tasks.
Design agent workflows involving reasoning, planning, tool usage, memory, and external systems.
Integrate LLMs including OpenAI, Claude, Gemini, and other AI models into applications.
Implement LLM tool/function calling and structured outputs.
Connect AI agents to external tools, databases, APIs, SaaS platforms, and internal systems.
Build multi-agent systems where specialized agents collaborate to complete complex workflows.
Implement agent memory, context management, retrieval systems, and state management.
Work with Model Context Protocol (MCP) and similar approaches for connecting AI systems to external tools.
Build AI-powered applications, internal business tools, SaaS products, and automated workflows.
AI-Assisted Development
Use modern AI development tools such as Claude, Claude Code, Base44, Lovable, Cursor, Replit, and similar platforms to accelerate development.
Use AI-assisted coding tools to prototype, build, debug, test, and iterate on applications.
Evaluate new AI models, development platforms, frameworks, and tools for practical use in software development.
Maintain engineering quality while using AI-assisted development workflows.
AI Reliability and Engineering
Implement error handling, retries, fallbacks, validation, and recovery mechanisms for AI workflows.
Build human-in-the-loop approval processes where required.
Implement appropriate agent permissions and controls.
Develop logging, monitoring, and observability for AI systems.
Test and evaluate AI systems to ensure they consistently perform their intended tasks.
Debug AI workflows when agents produce unexpected results or fail to complete tasks.
Implement API security, secret management, rate limiting, and other production controls.
Manage AI usage and infrastructure costs.
Implement background jobs, queues, and agent state management where required.
Deployment and Infrastructure
Deploy applications, backend services, and AI systems to cloud infrastructure.
Work with platforms such as AWS, GCP, Azure, Vercel, Railway, Render, Hetzner, or similar platforms.
Work with Docker and Linux environments where required.
Ensure applications are designed with scalability, security, performance, cost, and maintainability in mind.
Support production monitoring and troubleshooting.
Research and Development
Research and experiment with new AI models, frameworks, agent architectures, and development tools.
Work with frameworks such as LangChain, LangGraph, OpenAI Agents SDK, CrewAI, AutoGen, PydanticAI, or LlamaIndex.
Evaluate different approaches to agent orchestration, retrieval, memory, tool use, and workflow automation.
Continuously improve existing AI systems and development processes.
Required Qualifications
Proven software engineering experience building and deploying complete applications.
Strong experience with JavaScript/TypeScript, Python, or both.
Experience with React, Next.js, Node.js, FastAPI, or similar frameworks.
Strong understanding of REST APIs, webhooks, third-party integrations, authentication, and authorization.
Experience working with PostgreSQL, Supabase, MongoDB, or similar databases.
Experience using Git and GitHub.
Practical experience integrating LLMs into software applications.
Experience with AI agents, tool/function calling, structured outputs, prompt engineering, or RAG.
Understanding of agent architecture, including memory, context management, state management, tool use, and orchestration.
Experience deploying applications or backend services to cloud infrastructure.
Strong debugging and problem-solving skills.
Ability to take ownership of a project from idea through deployment.
Ability to independently learn and work with unfamiliar technologies.
Preferred Experience
Experience building and deploying AI agents into production.
Experience building SaaS or internal business applications.
Extensive experience with AI coding tools such as Claude Code, Cursor, Lovable, Base44, or Replit.
Experience building or integrating MCP servers and clients.
Experience with n8n, Make, Zapier, or similar workflow automation platforms.
Experience with Docker and Linux servers.
Experience with vector databases such as Pinecone, Qdrant, Weaviate, Supabase Vector, or pgvector.
Experience building real-time AI applications, voice agents, or conversational systems.
Experience with LangChain, LangGraph, OpenAI Agents SDK, CrewAI, AutoGen, PydanticAI, or LlamaIndex.

Work arrangement
Yes