Tech Stack

Description

You will design and implement cutting-edge AI solutions, building practical systems that leverage modern language models for real-world problems. This role involves prototyping quickly, iterating rapidly, and translating emerging model capabilities into reliable, production-ready systems.

Requirements

• At least 1+ year experience in AI engineering or research, or 3-5 years of experience in software engineering or similar roles
• Strong applied AI experience, including working knowledge of AI systems and AI APIs or open-source models
• Experience with vector databases (e.g., Pinecone, Weaviate, FAISS, Milvus) and retrieval-augmented generation (RAG) architectures

Responsibilities

• Design and implement AI-driven systems using AI APIs in creative and smart ways
• Build prototypes and production workflows that leverage language models for tasks such as classification, evaluation, and synthetic data generation
• Integrate AI APIs, vector stores, and supporting infrastructure to enable scalable applications
• Experiment with and evaluate both hosted and open-source models where appropriate
• Partner with product managers, analysts, and technical writers to translate complex systems into well-defined requirements and clear external materials
• Provide technical feedback to product and engineering teams to improve system quality and performance