Job VC
AI Developer
Technologies
Description
AI Developer (Remote)
Join a high-performing team building next-generation B2B AI agents. We are seeking an AI Developer to help evolve systems beyond simple LLM wrappers into sophisticated, production-grade agentic workflows with automated evaluation.
Key Responsibilities
Agent Development
Design, build, and maintain autonomous agents and multi-agent systems capable of handling complex business logic.
Agentic Systems Evolution
Transform existing LLM implementations into structured, tool-using workflows with memory, planning, and execution capabilities.
Testing & Evaluation
Develop robust evaluation frameworks (evals) to measure model performance, reduce hallucinations, and ensure output consistency.
Integration
Integrate AI workflows with internal APIs and third-party B2B tools to enable end-to-end automation.
Optimization
Continuously refine prompt engineering, orchestration logic, and structured data extraction to improve performance and cost efficiency.
Requirements
3+ years of software engineering experience (Python or TypeScript preferred)
Some Hands-on experience with LLM orchestration frameworks (e.g., LangChain, CrewAI, LlamaIndex)
Solid experience in API development and technical documentation
Experience building or implementing AI evaluation frameworks
Ability to work autonomously in a fast-paced, remote environment
Nice to Have
Familiarity with agent architectures (planning, reflection, memory)
Experience with AI observability tools (e.g., LangSmith, Weights & Biases)
Contributions to open-source AI projects
Join a high-performing team building next-generation B2B AI agents. We are seeking an AI Developer to help evolve systems beyond simple LLM wrappers into sophisticated, production-grade agentic workflows with automated evaluation.
Key Responsibilities
Agent Development
Design, build, and maintain autonomous agents and multi-agent systems capable of handling complex business logic.
Agentic Systems Evolution
Transform existing LLM implementations into structured, tool-using workflows with memory, planning, and execution capabilities.
Testing & Evaluation
Develop robust evaluation frameworks (evals) to measure model performance, reduce hallucinations, and ensure output consistency.
Integration
Integrate AI workflows with internal APIs and third-party B2B tools to enable end-to-end automation.
Optimization
Continuously refine prompt engineering, orchestration logic, and structured data extraction to improve performance and cost efficiency.
Requirements
3+ years of software engineering experience (Python or TypeScript preferred)
Some Hands-on experience with LLM orchestration frameworks (e.g., LangChain, CrewAI, LlamaIndex)
Solid experience in API development and technical documentation
Experience building or implementing AI evaluation frameworks
Ability to work autonomously in a fast-paced, remote environment
Nice to Have
Familiarity with agent architectures (planning, reflection, memory)
Experience with AI observability tools (e.g., LangSmith, Weights & Biases)
Contributions to open-source AI projects