Tech Stack: Python / Node.js, LLMs, AWS, APIs

Role Overview:

You ll build and integrate AI-driven features into the platform, working on orchestration, prompt design, and model integrations. This role focuses on applied AI, not research.

Responsibilities:

1. Design and implement AI workflows and orchestration services
2. Integrate with LLMs (OpenAI, Anthropic, etc.)
3. Build APIs to expose AI capabilities to backend and frontend services
4. Optimize prompt design and model interactions
5. Ensure secure, scalable AI service deployment on AWS
6. Monitor performance, latency, and cost of AI workloads
7. Collaborate closely with backend and product teams

Required Skills:

1. Experience working with LLMs and AI APIs
2. Strong programming skills in Python or Node.js
3. Experience building production-grade AI services
4. Understanding of prompt engineering and response evaluation
5. Experience deploying AI services in cloud environments

Nice to Have:

1. Experience with vector databases or embeddings
2. Knowledge of AWS AI services (Bedrock, SageMaker)
3. Familiarity with observability and tracing for AI workloads

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

AI Engineer

Job Description

No Referrers Available