Senior AI Developer

We are seeking a Senior AI Developer to own the design, development, and integration of AI-powered capabilities across ONEngine’s enterprise facilities management platform. You will build and maintain AI agent workflows, integrate large language model APIs into production systems, and develop the intelligent automation features that differentiate our product. Working closely with the CTO, backend engineers, and product teams, you will define AI development standards, drive adoption of AI-assisted engineering practices across the team, and ensure our AI systems are robust, observable, and production-ready. This is a hands-on senior IC role., * Design, build, and maintain AI agent workflows and multi-agent orchestration systems that power ONEngine’s intelligent automation features.

• Create internal applications utilizing AI to help our Operations Team.
• Integrate LLM APIs (Anthropic Claude, OpenAI, and similar) into backend services, building reliable, production-grade AI-powered features with proper error handling, fallback logic, and observability.
• Develop backend services and data pipelines in Python and TypeScript supporting AI inference, prompt management, context retrieval, and agent coordination.
• Implement Retrieval Augmented Generation (RAG) pipelines and vector search integrations to ground AI responses in ONEngine domain knowledge and customer data.
• Leverage AI-assisted development tools including Claude Code, GitHub Copilot, and similar to drive high personal and team-level development velocity.
• Champion and operationalize AI-assisted development practices across the engineering team, establishing workflows and standards that improve the productivity of all engineers.
• Evaluate, prototype, and recommend AI frameworks and tooling (LangChain, LlamaIndex, CrewAI, AutoGen, or similar) for agent orchestration and knowledge retrieval use cases.
• Build and maintain prompt engineering infrastructure including versioned prompt libraries, evaluation harnesses, and A/B testing frameworks.
• Design AI systems with production requirements in mind: latency budgets, cost management, token optimization, rate limiting, caching strategies, and graceful degradation.
• Implement monitoring and observability for AI systems including LLM call tracing, evaluation metrics, and output quality dashboards.
• Collaborate with DevOps to deploy and scale AI workloads on AWS using Lambda, ECS, API Gateway, and SQS.
• Participate in code reviews, architecture discussions, and product planning sessions as the primary AI technical voice.

Do you have experience in Python?, * Education: Bachelor’s or Master’s degree in Computer Science, Engineering, AI/ML, or a related technical discipline.

• Experience:

• 5+ years of professional software development experience, with at least 2 years focused on AI/ML systems or LLM-powered application development.

• Proven experience building production AI agent systems or multi-agent workflows using frameworks such as LangChain, LlamaIndex, CrewAI, AutoGen, or the Anthropic Agents SDK.

• Hands-on experience integrating LLM APIs (Anthropic Claude API, OpenAI API, or equivalent) into production backend services.

• Demonstrated use of AI coding tools (Claude Code, GitHub Copilot, Cursor, or similar) as a core part of day-to-day development workflow.

• Experience building RAG pipelines, vector databases (Pinecone, pgvector, Weaviate, or similar), and knowledge retrieval systems.

• Experience in agile, cross-functional product engineering teams delivering enterprise SaaS.

• Skills:

• Deep proficiency in Python for AI/ML workloads, data pipelines, scripting, and backend service development.

• Strong proficiency in TypeScript and Node.js for backend service integration and API development.

• Expertise in AI agent architecture patterns: tool use, memory management, context windows, planning loops, and multi-agent coordination.

• Hands-on proficiency with AI-assisted development tools-specifically Claude Code-and a strong point of view on how to use them effectively to accelerate engineering output.

• Experience with prompt engineering best practices: few-shot prompting, chain-of-thought, structured output, system prompt design, and evaluation.

• Solid understanding of LLM APIs including context management, token budgeting, streaming, function/tool calling, and cost optimization.

• Experience building and consuming RESTful APIs with a strong understanding of API security (OAuth, JWT).

• Familiarity with AWS cloud services (Lambda, API Gateway, SQS, S3, ECS) for deploying AI workloads.

• Experience with CI/CD pipelines, containerization (Docker), and cloud deployment workflows.

• Strong written and verbal communication skills; ability to explain AI system behavior and tradeoffs to non-technical stakeholders.

• Nice to Haves:

• Experience with the Anthropic Claude API specifically, including extended thinking, tool use, and multi-turn agent patterns.

• Familiarity with the Model Context Protocol (MCP) for agent-tool integration.

• Background in field service management, facilities management, CMMS, or B2B enterprise SaaS.

• Experience with fine-tuning, RLHF, or model evaluation methodologies.

• AWS certifications (Solutions Architect, ML Specialty, or Developer Associate).

• Contributions to open-source AI tooling or published writing on AI engineering practices.

Tech Stack

Python, TypeScript, Anthropic Claude API, OpenAI API, LangChain / LlamaIndex / CrewAI, Claude Code, pgvector / Pinecone, PostgreSQL, AWS Lambda, API Gateway, SQS, ECS, S3, Docker, GitHub Actions, Jest, Pytest

4.94.9 out of 5 stars Remote $10 - $80 an hour - Full-time