AI Architect

Qtsolv; Pune District; On-site; INR 3,000,000 - 4,200,000; Full time

Job summary

Qtsolv in Pune seeks an experienced AI Architect to design and implement enterprise-grade AI solutions using LLMs, RAG, and prompt engineering, with an emphasis on integrating AI into existing business ecosystems.

You will define AI architecture standards, govern data and models, oversee DFMEA and Functional Safety practices, and mentor teams on GenAI deployment across edge and cloud environments.

Qualifications

• Experience with Large Language Models (LLMs) and edge deployments.
• Hands-on prompt engineering and model optimization.
• Experience designing RAG architectures and vector databases.
• Knowledge of AI governance, security, and responsible AI.
• Familiarity with DFMEA and Functional Safety standards.

Responsibilities

• Design and architect scalable GenAI solutions for enterprise use cases.
• Develop and optimize prompt engineering frameworks to improve accuracy.
• Build RAG pipelines using vector databases, embeddings, and knowledge repos.
• Integrate AI/LLM solutions with existing APIs and enterprise platforms.
• Evaluate LLMs for edge and cloud deployments considering performance, latency, and security.
• Mentor engineering teams on GenAI technologies and deployment strategies.
• Ensure compliance with governance, regulatory standards, and safety practices.
• Collaborate with cross-functional teams to embed AI capabilities into products.

Skills

LLMs

Prompt Engineering

RAG architectures

Vector Databases

APIs integration

Python

AI Governance

Functional Safety

Tools

Vector databases

Embeddings

Job description

We are seeking an experienced AI Architect to design and implement enterprise-grade AI solutions leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and advanced Prompt Engineering techniques. The ideal candidate will have expertise in integrating AI solutions into existing business ecosystems and a strong understanding of Functional Safety Engineering and DFMEA (Design Failure Mode and Effects Analysis) processes.

Key Responsibilities

• Design and architect scalable AI/GenAI solutions utilizing Edge LLMs, cloud-based LLMs, and hybrid AI architectures.
• Develop and optimize Prompt Engineering frameworks to improve model accuracy, reliability, and business outcomes.
• Design and implement RAG (Retrieval-Augmented Generation) pipelines using vector databases, embeddings, and enterprise knowledge repositories.
• Integrate AI/LLM solutions with existing applications, APIs, enterprise platforms, and business workflows.
• Evaluate, select, and optimize LLMs for edge and enterprise deployments based on performance, latency, security, and cost requirements.
• Collaborate with cross-functional teams to incorporate AI capabilities into products while ensuring compliance with business and regulatory standards.
• Apply Functional Safety Engineering principles to AI-enabled systems, identifying potential risks and ensuring safe operation.
• Support DFMEA activities by assessing AI-related failure modes, risks, and mitigation strategies during product development.
• Define AI architecture standards, governance frameworks, and best practices for enterprise adoption.
• Mentor engineering teams on AI architecture, GenAI technologies, and deployment strategies.

Required Skills

• Strong experience with Large Language Models (LLMs), including Edge LLM deployments.
• Hands‑on expertise in Prompt Engineering and prompt optimization techniques.
• Experience designing and implementing RAG architectures.
• Knowledge of vector databases, embeddings, semantic search, and knowledge retrieval systems.
• Experience integrating AI/LLM solutions with enterprise applications and APIs.
• Proficiency in Python and AI/ML frameworks.
• Understanding of AI governance, model evaluation, security, and responsible AI practices.
• Experience with Functional Safety Engineering standards and methodologies.
• Strong knowledge of DFMEA (Design Failure Mode and Effects Analysis) processes.

Preferred Qualifications

• Experience with automotive, industrial, manufacturing, or safety‑critical systems.
• Knowledge of Edge AI deployment frameworks and model optimization techniques.
• Familiarity with cloud platforms such as AWS, Azure, or GCP.
• Experience with MLOps, AI lifecycle management, and production AI deployments.

Experience

• 10+ years of overall software/engineering experience.
• 5+ years of experience in AI/ML architecture, GenAI, or enterprise AI solution design.

Nice to Have

• Experience with autonomous systems, digital engineering, or intelligent product development.
• Certifications in AI, Cloud, or Functional Safety domains.