AI Engineer

Responsibilities:

• Build and iterate on prompt pipelines and multi-agent workflow components.
• Design and integrate agentic workflows to orchestrate multi-step, tool-using agents that plan, call models, and hand off between stages in production.
• Deploy and serve open-source models, set up inference endpoints, manage GPU compute, and optimize for latency and cost
• Write evals, compare outputs against references, quantify quality, and feed results back into the pipeline
• Work on data pipelines: structured extraction from messy source text, localization, similarity/dedup
• Debug and maintain pipeline stages in production.

Requirements:

• Basic (1+/3+) years of engineering experience, or a strong portfolio of shipped projects.
• Solid Python fundamentals; clean, working, readable code.
• Hands-on experience with LLM APIs and prompt engineering (personal projects count).
• Comfort with Git, REST APIs, and working in a Linux environment.
• A feel for content and narrativeyou can judge whether generated output is actually good, not just valid.
• Curiosity and clear communication: you ask good questions and stay silent.

Preferred:

• Exposure to agent/orchestration frameworks (LangGraph, LangChain, CrewAI).
• Familiarity with vector databases, embeddings, or RAG (Qdrant, pgvector).
• Hands-on work with open-source generative media models Flux, LTX, Wan, or similar.
• Experience deploying open-source models for inference (vLLM, ComfyUI, Replicate/Cog, Docker + GPU).
• Experience writing evals or LLM-as-judge scoring.
• Node.js and FastAPI familiarity, or experience deploying on AWS.