Artificial Intelligence Engineer

ClanX; Mumbai; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

ClanX in Mumbai is hiring a backend engineer to design and ship LLM-powered features on a NestJS/TypeScript stack. You will own orchestration, tool calls, memory, and evaluation for reliable agents and multi-step pipelines, selecting models by quality, latency and cost.

Build RAG-grounded responses using embeddings and MongoDB/Elasticsearch, while improving streaming and caching to maximize performance. You will collaborate with the founder, backend engineers, and product team to iterate on

Qualifications

• 2+ years of software engineering experience with TypeScript/Node.js.
• Experience shipping an LLM-powered feature to production.
• Hands-on with OpenAI, Gemini, or Anthropic APIs.
• Knowledge of embeddings, vector search, and RAG patterns.
• Production experience with MongoDB, Elasticsearch, or Redis.
• Ability to balance quality, latency and cost.
• Experience owning a module from unclear requirements to a shipped feature.
• Bachelor’s degree or equivalent practical experience.

Responsibilities

• Design and build LLM-powered chat, content understanding and recommendation features on the NestJS/TypeScript backend.
• Own orchestration, tool calling, memory and evaluation for reliable agents and pipelines.
• Route models based on quality, latency, and cost.
• Build RAG systems using embeddings, MongoDB/Elasticsearch for grounding.
• Improve production performance with streaming, caching, token budgets, and queue-based processing.
• Develop tests and evaluation datasets from real user queries to track relevance and groundedness.
• Collaborate with founder, backend engineers, and product team to iterate on features.

Skills

TypeScript

Node.js

NestJS

LLM integration

Prompt design

Streaming

Embeddings

Vector search

RAG patterns

Latency optimisation

Module ownership

AWS basics

Education

Bachelor’s degree in CS/Engineering or equivalent

Tools

MongoDB

Elasticsearch

Redis

Qdrant

AWS (EC2/Beanstalk, S3, SQS)

Job description

Job Description:

Requirements

• 2 years of software engineering experience with strong TypeScript and Node.js skills. NestJS experience is preferred.
• Shipped at least one LLM-powered feature to production, such as an assistant, RAG system, or content extraction pipeline.
• Hands-on experience with Gemini, OpenAI, or Anthropic APIs, including prompt design, structured outputs, tool calling, and streaming.
• Working knowledge of embeddings, vector search, and RAG patterns.
• Production experience with MongoDB, Elasticsearch, or Redis.
• Ability to balance AI response quality, latency, and cost based on user needs.
• Experience owning a module from unclear requirements to a shipped feature with minimal oversight.
• Familiarity with AWS fundamentals, including EC2 or Beanstalk, S3, and SQS.
• Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
• Bonus: LLM evaluation pipelines, LangGraph, LangChain, MCP, prompt caching, model routing, or LLM cost optimisation.
• Bonus: WhatsApp Cloud API, Instagram Graph API, or experience at an AI-focused startup.

Responsibilities

• Design, build, and improve LLM-powered chat, content understanding, and recommendation features on the NestJS and TypeScript backend.
• Own orchestration, tool calling, memory, and evaluation for reliable agents and multi-step pipelines.
• Select and route proprietary and open-source models based on quality, latency, and cost.
• Build RAG systems using embeddings, Qdrant, Elasticsearch, and MongoDB to ground responses in first-party data.
• Improve production performance through SSE streaming, prompt caching, token budgets, Redis session state, and SQS-based processing.
• Build automated tests and evaluation datasets from real user queries to track relevance, response quality, and groundedness.
• Monitor production behaviour and iterate on features with the founder, backend engineers, and product team.

Job Details

Mumbai, work from office.

Interview Process

• Initial Screening
• Technical Interview
• Founder Discussion