Technical Lead - AI & Engineering

Fastsurance Consultants; Dadri; On-site; INR 2,600,000 - 4,200,000; Full time

Job summary

Fastsurance Consultants is seeking a Technical Lead to own AI & Engineering initiatives, driving design and delivery of production-grade AI systems with Backend. You will lead a cross-functional engineering team and champion scalable architectures.

The role emphasizes hands-on implementation in Python and Node.js, LLM-based pipelines, and cloud platforms (Azure). You will mentor engineers, oversee security and cost optimization, and collaborate with product stakeholders to convert requirements

Qualifications

• Hands-on experience with LLMs and RAG pipelines.
• Strong backend and distributed system design capabilities.
• Proficiency in Python and Node.js/TypeScript with web frameworks.

Responsibilities

• Design and deploy LLM-powered pipelines with RAG and agentic workflows.
• Architect distributed backend systems using Kafka, Redis, and Azure cloud.
• Design end-to-end AI app architecture including LLM orchestration and vector databases.
• Lead and mentor a backend engineering and QA team.
• Own infrastructure decisions including cloud, cost optimization, and security/compliance.
• Collaborate with product stakeholders to translate requirements into scalable tech solutions.
• Drive evaluation, prompt engineering, and continuous improvement of AI system accuracy.

Skills

LLM pipelines

RAG workflows

Vector search

Prompt engineering

Python

Node.js/TypeScript

Distributed systems design

System design

Team leadership

Tools

Kafka

Redis

MongoDB

Docker

Azure

FastAPI/Express.js

Job description

About the Role

We're looking for a Technical Lead to own our AI & Engineering initiatives, driving the design and delivery of production-grade AI systems with Backend System while leading a cross-functional engineering team.

This is a hands-on engineering leadership role focused on building production-grade AI applications and scalable backend systems. It is not primarily a research or model-training role.

Key Responsibilities

• Design and deploy LLM-powered pipelines, including RAG, agentic workflows
• Architect distributed backend systems using Kafka, Redis, and cloud infrastructure (Azure)
• Design end-to-end AI application architecture covering LLM orchestration, RAG, vector databases, model APIs, evaluation, observability, and backend services.
• Lead and mentor a team of backend engineers & QA
• Own infrastructure decisions including cloud, cost optimization, and security/compliance practices
• Collaborate with product and business stakeholders to translate requirements into scalable technical solutions
• Drive evals, prompt engineering, and continuous improvement of AI system accuracy and reliability

Required Skills

• Strong hands-on experience with LLM , RAG pipelines, vector search, and prompt engineering
• Proficiency in Python and Node.js/TypeScript; experience with FastAPI/Express.js
• Experience with Kafka, Redis, MongoDB, and distributed system design
• Working knowledge of LLM APIs (OpenAI, Gemini)
• Cloud experience (Azure) and containerization (Docker)
• Proven experience leading and mentoring engineering teams

Must Have

• Proficiency in Node JS, Python and MongoDB
• Distributed System Skills
• System Design Skills
• Hands on experience in Designing and Maintaining Backend System

Good to Have

• Experience building AI agents and RAG based system
• Exposure to OCR and multi-modal document pipelines
• Familiarity with security/compliance frameworks such as ISO 27001