Job Description

ROLES & RESPONSIBILITIES

:

Generative AI Architect (AWS)

Job Summary

We are seeking an experienced Generative AI Architect with deep expertise in designing, building, and scaling Generative AI and Large Language Model (LLM)-based solutions on cloud platforms. The role requires strong architectural leadership and hands-on implementation skills, particularly using Python-based AI/ML frameworks, to deliver secure, scalable, and production-grade GenAI systems.


________________________________________

Eligibility

Minimum Qualifications

Bachelor's degree in Computer Science, Engineering, or a related field

OR Master's degree in Statistics, Data Science, Economics, Operations Research, or a related discipline.

12-15+ years of experience in Analytics, Data Science, AI/ML, or advanced engineering roles. Extensive hands-on experience with Generative AI and LLM-based solutions. Strong proficiency in Python, with experience building AI/ML and GenAI applications. Proven experience designing and deploying solutions on AWS. Solid understanding of data engineering, model lifecycle management, and production deployment.

________________________________________

Core Technical Skills (Required)

Generative AI & LLM Architecture

Expertise in:

o Prompt design and prompt engineering using Python-based frameworks


o Retrieval-Augmented Generation (RAG), Corrective RAG, and hybrid retrieval approaches


o Knowledge Graph-based RAG implementations


o Multi-agent and agentic frameworks implemented in Python


o Model evaluation, hallucination mitigation, and response quality measurement

Experience with:

o Fine-tuning techniques such as LoRA / QLoRA using Python ML stacks


o Reranking, embedding strategies, and semantic search optimization


o Automated and human-in-the-loop evaluation frameworks

Python & AI/ML Development

Advanced proficiency in Python for:

o Developing GenAI services, APIs, and orchestration layers


o Integrating LLMs with vector databases, search engines, and data sources


o Building reusable libraries and modular AI components

Experience with Python libraries and frameworks such as:

o LangChain, LangGraph, LlamaIndex or similar


o FastAPI or Flask for AI service deployment


Multimodal AI

Experience or strong architectural exposure to:

o Text, image, audio, and video AI workflows


o Multimodal generation pipelines orchestrated via Python services


o Content structuring, summarization, and transformation using GenAI

AWS & Cloud Architecture

Strong hands-on experience with AWS services, including:

o Amazon Bedrock, SageMaker


o Lambda, ECS/EKS


o S3, OpenSearch, DynamoDB, RDS


o IAM, VPC, KMS, CloudWatch

Experience designing:

o Secure, scalable, and cost-optimized GenAI architectures


o VPC-isolated AI workloads and governed access models


o CI/CD pipelines and Python-based MLOps workflows


Data & Platform Engineering

Solid understanding of:

o ETL pipelines implemented in Python


o Structured and unstructured data processing


o SQL and database technologies

Exposure to Big Data and distributed processing frameworks is desirable.

________________________________________

Key Responsibilities

Architecture & Solution Design

Design end-to-end architectures for Python-driven Generative AI and LLM solutions. Define reusable Python frameworks for prompt management, RAG pipelines, agent orchestration, and evaluation. Ensure architectural alignment with scalability, security, and governance standards.

Technical Leadership & Delivery

Lead solution development using Python-centric AI stacks, from design through production deployment. Guide engineering teams on best practices for Python-based GenAI development. Ensure delivery of high-quality, production-ready AI solutions.

Governance, Quality & Risk Management

Implement governance, safety controls, and evaluation frameworks using Python-based tooling. Monitor performance, quality, and reliability of deployed GenAI systems.

Mentoring & Best Practices

Mentor engineers and data scientists on Python, GenAI architecture, and LLM integration patterns. Conduct code and design reviews to ensure maintainability and quality.

Innovation & Continuous Learning

Stay current with advancements in Generative AI and Python-based AI ecosystems. Evaluate and adopt new frameworks, tools, and methodologies where relevant.

________________________________________

Desirable Skills

Experience with open-source LLMs and SLMs using Python. Familiarity with vector databases and embedding stores. Exposure to observability and evaluation tooling for GenAI systems. Understanding of content structuring or learning-related AI workflows is a plus.
EXPERIENCE


20-25 Years
SKILLS


Primary Skill: Data Science
Sub Skill(s): Data Science
Additional Skill(s): Python, Data Modeling, Data Science
ABOUT THE COMPANY


Infogain is a human-centered digital platform and software engineering company based out of Silicon Valley. We engineer business outcomes for Fortune 500 companies and digital natives in the technology, healthcare, insurance, travel, telecom, and retail & CPG industries using technologies such as cloud, microservices, automation, IoT, and artificial intelligence. We accelerate experience-led transformation in the delivery of digital platforms. Infogain is also a Microsoft (NASDAQ: MSFT) Gold Partner and Azure Expert Managed Services Provider (MSP).



Infogain, an Apax Funds portfolio company, has offices in California, Washington, Texas, the UK, the UAE, and Singapore, with delivery centers in Seattle, Houston, Austin, Krakow, Noida, Gurgaon, Mumbai, Pune, and Bengaluru.