AI / ML Engineer

We are looking for an AI/ML Engineer to build and scale the AI capabilities powering our products. The role focuses on LLM applications, AI agents, RAG, memory, tool calling, evaluation and the backend services required to run these systems reliably in production. You will own AI features end-to-end from prototype to production, working closely with product, backend and infrastructure teams.

Responsibilities:

• Build production applications using LLMs and AI agents.
• Design multi-step workflows with tool/function calling.
• Build and improve RAG, retrieval and context management pipelines.
• Implement conversation state and memory for AI applications.
• Build structured and streaming LLM workflows.
• Develop backend APIs and services supporting AI features.
• Evaluate, debug and improve AI system quality and reliability.
• Work with product, backend and infrastructure teams to ship AI capabilities to production.

Requirements:

• 2-6 years of AI/ML engineering experience.
• Strong programming skills in Python; experience with other programming languages is a plus.
• Hands-on experience building applications using LLMs.
• Experience with AI agents or multi-step LLM workflows.
• Good understanding of RAG, embeddings, vector search and retrieval.
• Experience with tool/function calling and structured outputs.
• Experience building backend APIs using FastAPI or similar frameworks.
• Good understanding of asynchronous programming and databases.
• Strong debugging and problem-solving skills.
• Ability to take AI features from prototype to production.

Good to Have / Bonus Points:

• LangGraph, LangChain or similar frameworks.
• Vector databases and reranking.
• LLM evaluation and observability.
• Knowledge graphs or graph-based retrieval.
• Redis or messaging/queue systems.
• Docker, Kubernetes and cloud platforms.