Python AI Engineer

Experis; Pune District; On-site; INR 1,200,000 - 2,400,000; Full time

Job summary

Experis in Pune is seeking a Python AI Engineer to build production backend services and design RAG and agentic AI systems on Microsoft Azure. This hands-on role covers API development, cloud data pipelines, and LLM-powered conversational agents - not a pure research or pure DevOps role.

You will design, implement, and tune retrieval pipelines, integrate with AI systems via REST, manage Azure infrastructure, and document architecture decisions for technical stakeholders.

Qualifications

• Experience building Python backends with FastAPI or similar.
• Hands-on with OAuth2 and data encryption in transit.
• Experience with Azure AI search or vector databases (Elasticsearch, Pinecone, Weaviate).
• Knowledge of RAG, prompts, grounding, and citations.
• Experience with cloud-native patterns and observability tools.
• Git-based version control and code reviews.

Responsibilities

• Design, build, and maintain backend services using Python/FastAPI or equivalent.
• Integrate backend services with multiple upstream AI/chat systems via REST APIs.
• Build and tune retrieval pipelines on Azure AI Search, including indexing strategies, chunking, embeddings, hybrid/semantic search, and relevance evaluation.
• Design, configure, and evaluate AI agents using Microsoft Azure AI Foundry Agent Service or equivalent LLM agent/orchestration frameworks.
• Ground AI agents in enterprise knowledge sources with citations.
• Set up and manage Azure infrastructure, including Blob Storage data pipelines, API Management as an AI/API gateway, Managed Identities, RBAC, and Log Analytics for usage and cost monitoring.
• Evaluate new platform capabilities by distinguishing GA and preview features and assessing production readiness, support, and SLA implications.
• Communicate technical trade-offs clearly to stakeholders.
• Own end-to-end quality and test retrieval accuracy using realistic query patterns, including multi-part and comparison-style questions across large content catalogs.
• Write clear technical documentation covering architecture decisions and integration contracts for technical and non-technical stakeholders.

Skills

Python backend

REST APIs

Async programming

FastAPI

OAuth2

Azure AI Search

Vector search

LLM apps

RBAC

Git

Tools

Azure AI Foundry

Elasticsearch

Pinecone

Weaviate

Azure API Management

Swagger/OpenAPI

Job description

Position: Python AI Engineer

Job Type: Contract To Hire(C2H)
Experience: 34 Years
Location: Pune
Interview Mode: Unberry Assessment, Technical Interview (F2F)

Role Summary

We're looking for an engineer who can build production backend services and design/operate Retrieval-Augmented Generation (RAG) and agentic AI systems on Microsoft Azure. This is a hands-on role spanning API development, cloud data pipelines, and LLM-powered conversational agents - not a pure research or pure DevOps role.

Key Responsibilities

• Design, build, and maintain backend services using Python/FastAPI or equivalent.
• Integrate backend services with multiple upstream AI/chat systems via REST APIs.
• Build and tune retrieval pipelines on Azure AI Search, including indexing strategies, chunking, embeddings, hybrid/semantic search, and relevance evaluation.
• Design, configure, and evaluate AI agents using Microsoft Azure AI Foundry Agent Service or equivalent LLM agent/orchestration frameworks.
• Ground AI agents in enterprise knowledge sources with citations.
• Set up and manage Azure infrastructure, including Blob Storage data pipelines, API Management as an AI/API gateway, Managed Identities, RBAC, and Log Analytics for usage and cost monitoring.
• Evaluate new platform capabilities by distinguishing GA and preview features and assessing production readiness, support, and SLA implications.
• Communicate technical trade-offs clearly to stakeholders.
• Own end-to-end quality and test retrieval accuracy using realistic query patterns, including multi-part and comparison-style questions across large content catalogs.
• Write clear technical documentation covering architecture decisions and integration contracts for technical and non-technical stakeholders.

Required Skills & Experience

• Strong Python backend development experience.
• Experience with REST API design, async programming, and frameworks such as FastAPI or similar.
• Experience with Flask/Django is acceptable when combined with async/API design fundamentals.
• Hands-on experience with OAuth2/token-based authentication flows.
• Experience with API key/secret management and encryption of data in transit, such as AES-GCM or equivalent.
• Practical experience with Azure AI Search or comparable vector/hybrid search products such as Elasticsearch, Pinecone, or Weaviate.
• Experience with index design, indexers/data pipelines, embeddings, and relevance tuning.
• Experience building or integrating LLM-powered applications.
• Strong understanding of RAG pipelines, prompt/instruction design, function/tool calling, and citation/grounding patterns.
• Familiarity with cloud-native service patterns, including Managed Identities, RBAC, API gateways, and centralized logging/observability.
• Experience with Azure Monitor/Log Analytics or equivalent tools such as CloudWatch or Datadog.
• Ability to read vendor documentation and release notes and independently assess cloud AI capabilities for production use.
• Git-based version control and collaborative code review experience.

Preferred / Nice-to-Have

• Direct experience with Microsoft Azure AI Foundry Agent Service.
• Experience with Foundry IQ, Azure AI Search agentic retrieval, or Microsoft Copilot Studio.
• Experience designing chatbots/conversational agents supporting factual Q&A and multi-entity comparison-style questions over large product/document catalogs.
• Experience with Azure API Management or another API gateway for usage metering, rate limiting, and per-client governance.
• Background in regulated or compliance-sensitive industries such as financial services, healthcare, or insurance.
• Experience with data access boundaries and auditability.
• Exposure to markdown-based or structured-content knowledge bases as RAG data sources.