onsite

AI Engineer

As an AI Engineer, you will design, develop, and optimize AI-powered features, agents, and copilots. This role involves building and maintaining RAG pipelines, integrating AI models with various systems, and establishing testing and observability standards for AI applications. You will work with LLMs, vector databases, and AI orchestration frameworks to deliver production-grade AI solutions.

About the role

What you will do:

Design and develop AI-powered features, agents, and copilots.
Build and maintain RAG pipelines and knowledge retrieval systems.
Integrate AI models with internal systems, APIs, and business workflows.
Implement structured outputs, tool usage, and workflow orchestration.
Optimize AI systems for quality, latency, reliability, and cost.
Establish testing, evaluation, monitoring, and observability standards for AI applications.

Experience

2–5 years of overall software engineering experience.
1–2 years of hands-on AI/LLM application development experience.

Required Skills:

Strong proficiency in JavaScript/TypeScript and Node.js.
Hands-on experience building applications with LLMs (GPT, Claude, Gemini, Llama, etc.).
Experience with RAG, embeddings, vector databases, and semantic search.
Experience with AI orchestration frameworks such as LangChain, LangGraph, LlamaIndex, or similar.
Strong understanding of prompt engineering, agent architectures, and tool-calling patterns.
Familiarity with structured outputs, JSON schemas, and function-calling workflows.
Experience building REST APIs and integrating AI services into production applications.
Familiarity with async programming, streaming responses, and event-driven architectures.
Experience with testing strategies for AI systems, including unit testing, integration testing, and LLM output evaluation.
Experience with SQL/NoSQL databases and cloud platforms (AWS/GCP/Azure).
Familiarity with Docker, CI/CD, monitoring, and observability.

Preferred Skills:

Experience building multi-agent systems and workflow automation.
Experience with open-source LLMs and model hosting.
Knowledge of AI evaluation frameworks, guardrails, and observability tools.
Experience with cost tracking, token optimization, and performance tuning at scale.
Experience deploying production-grade AI applications serving real users.

About the role

What you will do:

Design and develop AI-powered features, agents, and copilots.
Build and maintain RAG pipelines and knowledge retrieval systems.
Integrate AI models with internal systems, APIs, and business workflows.
Implement structured outputs, tool usage, and workflow orchestration.
Optimize AI systems for quality, latency, reliability, and cost.
Establish testing, evaluation, monitoring, and observability standards for AI applications.

Experience

2–5 years of overall software engineering experience.
1–2 years of hands-on AI/LLM application development experience.

Required Skills:

Strong proficiency in JavaScript/TypeScript and Node.js.
Hands-on experience building applications with LLMs (GPT, Claude, Gemini, Llama, etc.).
Experience with RAG, embeddings, vector databases, and semantic search.
Experience with AI orchestration frameworks such as LangChain, LangGraph, LlamaIndex, or similar.
Strong understanding of prompt engineering, agent architectures, and tool-calling patterns.
Familiarity with structured outputs, JSON schemas, and function-calling workflows.
Experience building REST APIs and integrating AI services into production applications.
Familiarity with async programming, streaming responses, and event-driven architectures.
Experience with testing strategies for AI systems, including unit testing, integration testing, and LLM output evaluation.
Experience with SQL/NoSQL databases and cloud platforms (AWS/GCP/Azure).
Familiarity with Docker, CI/CD, monitoring, and observability.

Preferred Skills:

Experience building multi-agent systems and workflow automation.
Experience with open-source LLMs and model hosting.
Knowledge of AI evaluation frameworks, guardrails, and observability tools.
Experience with cost tracking, token optimization, and performance tuning at scale.
Experience deploying production-grade AI applications serving real users.