LLM & Generative AI Engineer

Sequere Technologies; Mohali; On-site; INR 1,500,000 - 2,400,000; Full time

Job summary

Sequere Technologies is building cutting-edge AI products in Mohali, India. The role focuses on developing RAG pipelines, agentic workflows, and LLM-powered solutions for enterprise clients.

You will own production AI systems, design scalable backend services, and optimize prompts, latency, and cost across the stack.

Qualifications

• 3+ years of software engineering with GenAI focus.
• Hands-on experience with LangChain, LlamaIndex or similar.
• Strong Python and API integration skills.
• Understanding of vector databases such as Pinecone/Weaviate/pgvector.
• Experience across full stack from model to UI.

Responsibilities

• Build and maintain RAG pipelines for enterprise clients.
• Design multi-agent orchestration using LangChain or CrewAI.
• Integrate LLM APIs (OpenAI, Anthropic, Mistral) into backend services.
• Implement prompt engineering strategies and evaluation frameworks.
• Collaborate with clients to translate business requirements into AI solutions.
• Instrument and monitor LLM systems for quality, latency and cost.

Tools

LangChain

LlamaIndex

Python

APIs

Vector DBs

Job description

Job Summary

Youll work at the bleeding edge of generative AI - building RAG pipelines, agentic workflows, and LLM-powered products that are already shaping industries. This is a high-impact role with direct ownership over production AI systems.

Responsibilities

• Build and maintain RAG (Retrieval-Augmented Generation) pipelines for enterprise clients
• Design multi-agent orchestration systems using frameworks like LangChain or CrewAI
• Integrate LLM APIs (OpenAI, Anthropic, Mistral) into scalable backend services
• Implement prompt engineering strategies and evaluation frameworks
• Work closely with clients to translate business requirements into AI solutions
• Instrument and monitor LLM systems for quality, latency, and cost

Requirements

• 3+ years of software engineering experience with 1+ years in LLM/GenAI
• Hands-on experience with LangChain, LlamaIndex, or similar frameworks
• Strong Python and API integration skills
• Understanding of vector databases (Pinecone, Weaviate, pgvector)
• Comfortable working across the full stack from model to UI

Nice to Have

• Experience with open-source model deployment (Ollama, vLLM, TGI)
• Knowledge of fine-tuning workflows (LoRA, QLoRA, PEFT)
• Prior startup or consulting experience