Artificial Intelligence Engineer

Trademo; Gurugram District; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Trademo is seeking a highly driven AI Engineer to join our product engineering team to design and deploy Agentic AI systems, RAG pipelines, and LLM-powered workflows that solve business problems at scale.

You will work with LangChain, LlamaIndex, vector databases, and OpenAI or open-source models to build production-grade AI products and push the boundaries of generative AI.

Qualifications

• 2-4 years of software engineering or AI/ML engineering experience in a product-based company.
• Hands-on experience with RAG architecture, embeddings, vector search, and retrieval systems. Experience working with LLMs and APIs such as OpenAI models or open-source alternatives.
• Hands-on experience with vector databases and production-grade API/backend development.
• Familiarity with cloud platforms such as AWS, Google Cloud, or equivalent.

Responsibilities

• Design, build, and optimize Agentic AI workflows for autonomous decision-making and task execution.
• Develop and deploy RAG pipelines integrating vector databases, retrieval systems, and LLM orchestration frameworks.
• Build AI applications leveraging modern LLM frameworks such as LangChain, LlamaIndex, and similar orchestration tools.
• Fine-tune prompts, optimize inference performance, and improve model output quality.
• Integrate AI services with APIs, backend systems, and product workflows.
• Work closely with product and engineering teams to ship scalable AI-first features.
• Evaluate emerging AI models, frameworks, and agent architectures to improve system performance.
• Build monitoring, evaluation, and feedback loops for continuous model improvement.

Skills

Python

API development

Backend engineering

Prompt engineering

Model evaluation

Production deployment

Cloud platforms

RAG architecture

Vector databases

LangChain

LLM integration

Tools

Pinecone

Weaviate

Job description

We are looking for a highly driven AI Engineer to join our product engineering team and build cutting-edge AI-powered applications. You will work on designing and deploying Agentic AI systems, RAG (Retrieval-Augmented Generation) pipelines, and LLM-powered workflows that solve real-world business problems at scale.

This role is ideal for someone who enjoys building production-grade AI products and experimenting with the latest advancements in generative AI.

What You’ll Do?

• Design, build, and optimize Agentic AI workflows for autonomous decision-making and task execution.
• Develop and deploy RAG pipelines integrating vector databases, retrieval systems, and LLM orchestration frameworks.
• Build AI applications leveraging modern LLM frameworks such as LangChain, LlamaIndex, and similar orchestration tools.
• Fine-tune prompts, optimize inference performance, and improve model output quality.
• Integrate AI services with APIs, backend systems, and product workflows.
• Work closely with product and engineering teams to ship scalable AI-first features.
• Evaluate emerging AI models, frameworks, and agent architectures to improve system performance.
• Build monitoring, evaluation, and feedback loops for continuous model improvement.

What are we looking for?

• 2-4 years of software engineering or AI/ML engineering experience in a product-based company. Strong hands-on experience building Agentic AI systems and autonomous AI workflows.
• Proven experience with RAG architecture, embeddings, vector search, and retrieval systems. Experience working with LLMs and APIs such as OpenAI models or open-source alternatives. Hands-on experience with vector databases like Pinecone, Weaviate, or similar tools.
• Strong proficiency in Python, API development, and backend engineering fundamentals. Understanding of prompt engineering, model evaluation, and production deployment.
• Familiarity with cloud platforms such as Amazon Web Services, Google Cloud, or equivalent.