AI Engineer 1

Role Overview

As an AI Engineer, you will build applications that leverage language models, specifically focusing on agentic applications that decompose goals into actionable steps, utilize tools, and interface with data sources. You will be responsible for the end-to-end lifecycle of these systems, from design and coding to production monitoring and cost optimization.

Responsibilities

• Build product features using language models, including API calls, prompt engineering, and MCPs.
• Implement retrieval-augmented generation (RAG) workflows involving chunking, embeddings, and vector search.
• Develop autonomous agents capable of multi-step task automation and error recovery.
• Manage the quality loop through test sets, A/B testing, and prompt tuning.
• Deploy and maintain production systems with a focus on logging, monitoring, and cost management.
• Evaluate and select foundation models from providers like Anthropic, Google, or OpenAI based on accuracy, speed, and cost.

Requirements

• Proven experience building AI projects (side projects, hackathons, or personal tools) that connect models to real-world tasks.
• Strong engineering fundamentals with proficiency in Python.
• Proficiency with Git, debugging, and technical documentation.
• 0-2 years of experience with a strong background in Engineering or Machine Learning.

Nice to Have

• Experience with GenAI libraries such as LangChain, LangGraph, or Hugging Face.
• Experience with vector databases like Pinecone, Weaviate, or Chroma.
• Experience with production software deployment, monitoring, or cost control.
• A public GitHub profile or technical write-ups.

Skills

• Python
• Large Language Models
• RAG
• Vector Databases
• Prompt Engineering