Engineering Architect

Persistent

12–16 yrs Pune Full Time Hybrid (office + remote)
Persistent logo
Posted : today
Actively hiring

Job description

Join a leading AI-driven digital engineering partner that empowers clients to anticipate future trends and achieve competitive advantages. We collaborate with industry pioneers, including Fortune 50 companies and top financial institutions, driving innovation through a disruptor's mindset and agility. Our sustained growth is a testament to our commitment to client success and a dynamic work environment. Recognized for innovation, leadership, and inclusion, we offer a robust platform for professional development.

This role is for an experienced Engineering Architect focused on designing and developing enterprise-scale Generative AI platforms, Agentic AI frameworks, and Retrieval-Augmented Generation (RAG) solutions. The ideal candidate will bring deep expertise in Python, FastAPI, Large Language Models (LLMs), cloud-native architectures, and AI engineering best practices.

Responsibilities

Architect and develop scalable Python and FastAPI-based microservices for AI, RAG, and GenAI workloads. Design and implement RAG frameworks for enterprise AI applications, defining strategies for ingestion, chunking, embedding, indexing, retrieval, reranking, and grounding. Build Agentic AI frameworks incorporating tool-calling, autonomous workflows, guardrails, and policy enforcement. Develop reusable AI accelerators, SDKs, frameworks, libraries, and templates. Architect and optimize Vector Database solutions using technologies like pgvector, Qdrant, Pinecone, OpenSearch, or Elasticsearch. Evaluate and integrate LLMs and foundation models based on business needs, performance, governance, and cost. Implement enterprise-grade security, authentication, authorization, governance, and compliance standards for AI platforms. Design cloud-native AI architectures leveraging AWS, Azure, and Google Cloud Platform. Develop robust CI/CD pipelines for AI applications and microservices deployments, utilizing containerization with Docker and Kubernetes. Implement monitoring, observability, logging, and operational support using OpenTelemetry and modern observability platforms. Drive performance tuning, scalability, and optimization of AI systems. Collaborate with Product Managers, Data Engineers, ML Engineers, and Enterprise Architects to define AI roadmaps and strategies. Lead architecture reviews, design workshops, and technical mentoring initiatives, promoting AI platform adoption and engineering best practices.

Qualifications

A minimum of 12-16 years of experience in Software Engineering, Solution Architecture, Platform Engineering, or Cloud Architecture is essential.

Possess strong expertise in Python development and enterprise application design, with hands-on experience in FastAPI, Flask, REST APIs, and microservices architecture. Demonstrated experience designing and deploying Generative AI and LLM-powered applications, including building Agentic AI frameworks and autonomous AI workflows. In-depth understanding of RAG architectures and implementation patterns, including embeddings, semantic search, vector retrieval, reranking, and contextual grounding. Proficiency with Vector Databases such as pgvector, Qdrant, Pinecone, Weaviate, OpenSearch/Elasticsearch. Experience integrating and deploying LLMs via Azure OpenAI, OpenAI APIs, Hugging Face Models, and open-source LLMs. Expertise in cloud-native architecture across AWS, Azure, and GCP, coupled with strong knowledge of Kubernetes, Docker, container orchestration, and distributed systems. Experience implementing CI/CD pipelines and DevOps practices is required, alongside a strong understanding of authentication, authorization, data protection, and AI governance principles. Familiarity with performance optimization, caching strategies, scalability, and high-availability architectures, including experience designing reusable frameworks and enterprise architecture patterns. Excellent communication, stakeholder engagement, and technical leadership capabilities are crucial for this role.

Essential Skills

PythonFastAPILarge Language Models (LLMs)Cloud-Native ArchitecturesAI EngineeringMicroservicesRetrieval-Augmented Generation (RAG)Agentic AI FrameworksVector DatabasesKubernetesDockerCI/CDDevOpsAWSAzureGCPREST APIsPlatform EngineeringSolution ArchitectureCloud ArchitectureOpenTelemetrypgvectorQdrantPineconeOpenSearchElasticsearchAzure OpenAIOpenAI APIsHugging Face ModelsWeaviateFlask

Highlights

  • Actively hiring

More Details

RoleEngineering Architect
IndustryInformation Technology & Services
DepartmentEngineering, Architecture, Information Technology
Employment TypeFull Time, Hybrid (office + remote)

About the Company

Persistent Systems logo

Persistent Systems

Information Technology & Services

Engineering Architect at Persistent | SkillMX | SkillMX