Project Role : Technology Architect

Project Role Description : Design and deliver technology architecture for a platform, product, or engagement. Define solutions to meet performance, capability, and scalability needs.

Must have skills : Generative AI

Good to have skills : Python (Programming Language)

Minimum 5 Year(s) Of Experience Is Required

Educational Qualification : 15 years full time education

Summary

We are seeking an experienced Full Stack Engineering Tech Lead with strong expertise in Generative AI, Agentic AI frameworks, and up-to-date cloud-native application architectures.

The role involves leading the design and development of enterprise-scale AI platforms, including RAG pipelines, agentic AI workflows, and microservices-based backend systems. The candidate will work closely with product owners, architects, and engineering teams to build scalable AI-driven applications deployed on cloud platforms like AWS or GCP.

The ideal candidate should combine deep hands-on engineering expertise with technical leadership, driving innovation and mentoring engineers while building production-grade AI systems.

Role: Full Stack Engineering Tech Lead (GenAI / Agentic AI Platforms)

Roles &

- Responsibilities:

Technical Leadership

Lead the design, architecture, and development of AI-driven full stack applications.

Provide technical direction and best practices for implementing Generative AI and Agentic AI solutions.

Mentor and guide full stack engineers and AI engineers.

Conduct architecture reviews, code reviews, and technical design discussions.

Drive engineering excellence, scalability, and security standards across AI applications.

AI / GenAI Platform Development

Architect and implement enterprise RAG (Retrieval Augmented Generation) pipelines.

Design agentic AI workflows and orchestration pipelines using LangGraph.

Develop scalable LLM inferencing pipelines using open-source or enterprise LLMs.

Design document ingestion pipelines including chunking, embedding, vectorization, and retrieval workflows.

Evaluate and experiment with emerging AI standards and technologies such as MCP (Model Context Protocol).

Design multi-agent orchestration frameworks for enterprise AI applications.

Backend &

- Microservices Architecture





Design and develop scalable microservices architecture using NestJS and Python.

Define standards for REST API design, versioning, and secure API development.

Implement event-driven integrations using webhooks and asynchronous communication patterns.

Design DAG-based workflows and orchestration pipelines for AI processing pipelines.

Data &

- AI Infrastructure

Architect vector database solutions for semantic search and AI retrieval systems using:
- pgVector
- OpenSearch
- Milvus

Design metadata and operational data storage architecture using PostgreSQL / AWS RDS. Implement distributed data processing pipelines using Apache Spark or equivalent frameworks.

Optimize embedding storage, indexing, and retrieval performance.

Cloud &

- Platform Engineering

Architect and deploy AI applications on AWS or GCP cloud platforms.

Design cloud-native AI architectures leveraging containerized workloads and managed services.

Define scalability, reliability, and resilience strategies for AI platforms.

Collaborate with DevOps teams to implement CI/CD pipelines for AI application deployments.

Security &

- Compliance

Implement secure coding practices for APIs and AI applications.

Ensure compliance with OWASP API security standards.

Design secure AI pipelines ensuring data protection and access control.

Establish security guardrails for AI integrations and data pipelines.

Architecture &

- Design

Translate functional business requirements into technical architecture and system design.

Design RAG architecture, retrieval strategies, and agentic AI workflows.

Develop architecture diagrams, solution blueprints, and system documentation using draw.io.

Define design patterns for AI orchestration, microservices, and cloud-native deployments.

Professional &

- Technical Skills:

AI &
- GenAI Technologies

LangChain

LangGraph

RAG pipeline architecture





Agentic AI orchestration

LLM inferencing pipelines

Knowledge of emerging AI protocols such as MCP

Programming Languages

Python

NestJS / Node.js

Databases

Vector Databases pgVector

OpenSearch

Milvus

Metadata Stores

PostgreSQL

AWS RDS

APIs &
- Integration

REST API development

Webhooks

Secure API design

OWASP API security practices

Data Processing

DAG-based processing pipelines

Apache Spark or distributed data processing frameworks

Cloud Platforms

AWS or GCP

Tools draw.io

Git-based development

CI/CD tools

Desired Skills

Experience with LLMOps / MLOps practices

Knowledge of prompt engineering and LLM evaluation

Experience with semantic search and embedding optimization

Exposure to multi-agent AI architectures

Experience building enterprise knowledge assistants or AI copilots

Mandatory Project Experience

Candidate must have hands-on implementation experience in enterprise AI systems, including at least one of the following:

RAG-based enterprise knowledge assistant

LLM inferencing platform

Agentic AI workflow using LangChain / LangGraph

Document ingestion and semantic search pipeline

Experience may come from industry projects, research initiatives, or AI platform development programs.

Leadership &

- Soft Skills

Strong technical architecture skills

Ability to mentor engineers and guide development teams

Hands on technical design and programming

Strong problem-solving and analytical thinking

Excellent communication and stakeholder management skills

Ability to translate functional requirements into scalable technical architectures

Strong innovation mindset and experimentation with emerging AI technologies

What We Value

We value leaders who

Drive innovation in Generative AI and modern engineering practices

Encourage experimentation and rapid prototyping

Build scalable and secure enterprise AI platforms

Foster continuous learning and technical excellence within engineering teams

6–10 Years of exp.

Additional Information

- The candidate should have minimum 5 years of experience in Generative AI.
- This position is based at our Mumbai office.
- A 15 years full time education is required.

📌 Technology Architect (Mumbai)
🏢 Accenture in India
📍 Mumbai