AI engineer

Overview

We’re looking for an AI engineer to help design, build, and deploy agentic systems that can reason, perform data science computations if needed, retrieve information, and interact with external tools. You’ll work on end-to-end development - from designing prompt workflows and evaluation pipelines to integrating APIs and orchestrating multiple agents in production.

This role is ideal for someone who enjoys rapid prototyping, structured experimentation, and building real, usable systems around large language models (LLMs).

What you'll do:

• Design, implement, and test multi-agent architectures and orchestration flows.
• Augment with data science and rule-based solutions if needed
• Build and refine prompting strategies, evaluation harnesses, and monitoring pipelines for LLM-based systems.
• Integrate models with retrieval systems, databases, and external APIs for real-world tasks.
• Prototype tools, reasoning modules, and adapters to expand agent capabilities.
• Work closely with product and backend teams to define clean interfaces between AI services and applications.
• Establish and maintain observability and performance metrics for agent behavior and response quality.
• Contribute to the design of continuous improvement loops for prompt and workflow optimization.

What We’re Looking For

• 1+ years of experience in software or ML development.
• Strong command of Python (FastAPI, LangChain, LlamaIndex, or similar frameworks).
• Familiarity with OpenAI, Anthropic, or other modern LLM APIs.
• Hands-on experience with RAG systems, vector databases (e.g., Pinecone, FAISS, Weaviate), or embeddings pipelines.
• Comfort working with RESTful APIs, structured JSON data, and asynchronous tasks.
• Ability to think experimentally — form hypotheses, run quick tests, measure, and iterate.
• Strong communication and documentation skills — you explain complex systems clearly.