Lead AI Engineer

Quantanite; Mumbai; On-site; INR 3,000,000 - 5,500,000; Full time

Benefits offered by this job

Dress code flexibility

Employee engagement programs

Professional development opportunities

Team events and outings

Values-driven culture

Job summary

Quantanite seeks a Lead AI Engineer to own end-to-end engineering for AI-driven product and client engagements. This hands-on role requires coding, prototyping, and setting technical standards to build scalable, secure, and cost-efficient AI applications.

You translate business needs into architecture, choose tech stacks, develop POCs, and ensure production-ready AI features while mentoring the team and aligning with security and performance goals.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Software Engineering, or a related field.
• 5-7 years of software engineering experience, including 2+ years in an architecture or technical leadership capacity.
• Hands on experience with LLMs (OpenAI, Claude, Gemini, Llama, etc.), GenAI frameworks (LangChain, LlamaIndex), and RAG-based architecture.
• Working knowledge of vector databases (Pinecone, FAISS, ChromaDB, Weaviate).
• Strong full stack development background: Python, JavaScript/TypeScript, and microservices (FastAPI, Flask, Node.js).
• Experience designing and deploying cloud-native solutions, Azure preferred, including deployment architecture and containerization.
• Practical experience with reinforcement learning / fine-tuning / RLHF-style optimization techniques for AI agents or models.
• Experience designing memory/context architectures for AI agents — short-term vs. long-term memory, retrieval strategies, and context window management.
• Familiarity with MCP (Model Context Protocol) or similar service-interoperability standards; comfortable designing API-first, composable service architectures.
• Solid grounding in data engineering and integration patterns — ETL, APIs, and data pipelines.
• Familiarity with Git, CI/CD pipelines, secure coding practices, and code review processes.
• Ability to produce clear architecture documentation — solution blueprints, technology architecture views, and design specifications.

Responsibilities

• Bridge business requirements and technical implementation — translate requirements into concrete technical designs and solution blueprints.
• Own the overall architecture and design for the product/project, including deployment architecture — application, data, integration, and infrastructure layers end to end.
• Determine the technology stack, frameworks, and LLM selection — evaluate languages, frameworks, LLM providers, vector stores, and orchestration tools.
• Establish AI engineering principles for the team — model selection criteria, prompting and evaluation standards, testing methodology, and production-ready criteria.
• Build hands-on prototypes and POCs to test technical concepts and de-risk approaches.
• Set minimum technical standards across AI applications — memory management, privacy, security, and cost efficiency.
• Establish MCP/API-style service architecture frameworks for interoperability across products and client systems.
• Design for scalability, latency, and cost-efficiency — non-functional requirements and architectural patterns.
• Drive design decisions through prototyping and trade-off analysis; lead architecture reviews.
• Define integration architecture with internal and external systems — APIs, data exchange mechanisms.
• Ensure code reviews, quality checks, and secure coding practices across the team.
• Own technical debt management and architecture documentation.
• Mentor developers on architectural best practices.
• Evaluate emerging GenAI capabilities and adoption opportunities.

Skills

LLMs (OpenAI, Claude, Gemini)

GenAI frameworks (LangChain, LlamaIdx)

RAG-based architecture

Vector databases (Pinecone, FAISS, Chs

Python

JavaScript/TypeScript

Microservices (FastAPI, Flask, Node.js

Azure cloud deployment

Reinforcement learning / RLHF

Memory/context architectures

API-first, service interoperability

Data engineering & ETL

Git, CI/CD, secure coding

Education

Bachelor’s or Master’s in CS/Software Eng

Tools

LangChain

LlamaIndex

Pinecone

FAISS

ChromaDB

Weaviate

VMs/Containerization

FastAPI

Flask

Node.js

Job description

Title - Lead AI Engineer

Job Description

Location: Mumbai, India

Reporting to: Global Technology Leader

About Quantanite

Quantanite is a customer experience (CX) and digital outsourcing solutions company helping fast-growing businesses and global brands rethink their operations. Through intelligent automation, GenAI, and exceptional people, we deliver measurable transformation and seamless service delivery across every touchpoint. Our global teams are passionate about innovation, agility, and purpose-driven results.

About the Role

We are seeking an Lead AI Engineer to own the end-to-end Lead Engineering for one or more of our AI-driven product and client engagements. This is a hands-on, product/project-scoped Lead Engineer role — someone who codes, prototypes, and sets the technical bar for how we build AI applications. You translate business requirements into a coherent technical solution, make the core stack and design decisions, and ensure what gets built is scalable, secure, and cost-efficient. You will personally develop proof-of-concepts to test new technical approaches, establish the engineering principles and minimum technical standards the team builds against, and design the service architecture that lets our AI capabilities plug into products and client systems cleanly. You will work closely with the team on day-to-day delivery and code-level design and the Tech PM who owns delivery timelines and prioritization, acting as the technical backbone that keeps architecture decisions sound as development moves fast and continuously.

Key Responsibilities

• Bridge business requirements and technical implementation — work with business stakeholders, Product, and the Tech PM to translate requirements into concrete technical designs and solution blueprints.
• Own the overall architecture and design for the product/project, including deployment architecture — application, data, integration, and infrastructure layers end to end.
• Determine the technology stack, frameworks, and LLM selection — evaluate and choose languages, frameworks, LLM providers, vector stores, and orchestration tools based on capability, cost, and maintainability.
• Establish AI engineering principles for the team — model selection criteria, prompting and evaluation standards, testing methodology, and what "production-ready" means for an AI feature.
• Build hands-on prototypes and POCs to test technical concepts, de-risk unproven approaches, and give the team a working reference before committing to a full build.
• Set minimum technical standards across AI applications for: reinforcement learning / fine-tuning approaches, memory and context management ("memory stacking") for agents, data privacy and security, and token consumption / inference cost efficiency.
• Establish MCP/API-style service architecture frameworks so AI capabilities are interoperable and can be integrated quickly across products and client systems, instead of being rebuilt per use case.
• Design for scalability, latency, and cost-efficiency — define non-functional requirements and architectural patterns (caching, async processing, model selection, infra sizing) to meet performance and budget targets.
• Drive major design decisions through hands-on prototyping and trade-off analysis (build vs. buy, pattern selection), not just review meetings.
• Lead architecture reviews and trade-off analysis (build vs. buy, pattern selection) and sign off before implementation begins.
• Define integration architecture with internal and external systems — APIs, data exchange mechanisms, and connections to enterprise and third-party platforms.
• Ensure code reviews, quality checks, coding standards, and secure coding practices are followed across the team, in partnership with the Tech Lead.
• Own technical debt management — track, prioritize, and plan remediation so shortcuts taken for speed don’t compound unmanaged.
• Produce and maintain architecture documentation — solution blueprints, technology architecture views, design specifications, and decision records.
• Mentor the developers on architectural best practices without taking over day-to-day implementation.
• Evaluate emerging GenAI/LLM capabilities and recommend adoption where it improves the product or delivery speed.

Required Skills & Qualifications

• Bachelor’s or Master’s degree in Computer Science, Software Engineering, or a related field.
• 5-7 years of software engineering experience, including 2+ years in an architecture or technical leadership capacity.
• Hands on experience with LLMs (OpenAI, Claude, Gemini, Llama, etc.), GenAI frameworks (LangChain, LlamaIndex), and RAG-based architecture.
• Working knowledge of vector databases (Pinecone, FAISS, ChromaDB, Weaviate).
• Strong full stack development background: Python, JavaScript/TypeScript, and microservices (FastAPI, Flask, Node.js).
• Experience designing and deploying cloud-native solutions, Azure preferred, including deployment architecture and containerization.
• Practical experience with reinforcement learning / fine-tuning / RLHF-style optimization techniques for AI agents or models.
• Experience designing memory/context architectures for AI agents — short-term vs. long-term memory, retrieval strategies, and context window management.
• Familiarity with MCP (Model Context Protocol) or similar service-interoperability standards; comfortable designing API-first, composable service architectures.
• Solid grounding in data engineering and integration patterns — ETL, APIs, and data pipelines.
• Familiarity with Git, CI/CD pipelines, secure coding practices, and code review processes.
• Ability to produce clear architecture documentation — solution blueprints, technology architecture views, and design specifications.

Preferred Experience

• Experience in BPO/outsourcing or high-volume, multi-client product delivery environments.
• Experience end-to-end engineering across multiple concurrent product feature builds or client implementations in an agile/hyper-agile delivery model.
• Familiarity with orchestration tools (Airflow, Prefect, LangGraph).
• Exposure to voice AI, OCR, vision-based AI, or multimodal models.

Soft Skills

• Able to explain technical trade-offs to non-technical stakeholders in plain terms.
• Comfortable making architectural calls under ambiguity and time pressure.
• High ownership — treats architecture quality as a personal accountability, not a checklist.
• Collaborative with Tech Lead and Tech PM; balances architectural rigor against delivery speed.
• Naturally curious and current with the latest AI/ML and GenAI developments.

Benefits

At Quantanite, we ask a lot of our associates, which is why we give so much in return. In addition to your compensation, our perks include:

• Dress: Wear anything you like to the office. We want you to feel as comfortable as when working from home.
• Employee Engagement: Experience our family community and embrace our culture where we bring people together to laugh and celebrate our achievements.
• Professional development: We love giving back and ensure you have opportunities to grow with us and even travel on occasion.
• Events: Regular team and organisation-wide get-togethers and events.
• Value orientation: Everything we do at Quantanite is informed by our Purpose and Values. We Build Better. Together.

Future Development

At Quantanite, you’ll have a personal development plan to help you improve in the areas you’re looking to develop in over the coming years. Your manager will dedicate time and resources to supporting you in getting you to the next level. You’ll also have the opportunity to progress internally — as a fast-growing organisation, our teams are growing, and you’ll have the chance to take on more responsibility over time.