AI Solutions Engineer

Ascendion Engineering; Hyderabad, Pune District, Bengaluru; Hybride; INR 2 500 000 - 5 000 000; Plein temps

Résumé du poste

Ascendion Engineering seeks an AI Solutions Engineer to architect, develop, and deploy enterprise AI apps using Generative AI, LLMs, Python, .NET/C#, and Azure Cloud. The role blends AI engineering with software practices to deliver scalable, secure solutions.

You will own the end-to-end lifecycle from design to production, building LLM-powered apps, RAG and agentic systems, and cloud-native platforms, with emphasis on security, observability, and Responsible AI.

Qualifications

• Hands-on experience building production-grade AI applications.
• Deep expertise in Generative AI, LLMs, prompt engineering, RAG, and Agentic AI.
• Experience designing multi-agent systems and AI orchestration workflows.
• Knowledge of LLM evaluation, grounding techniques, and Responsible AI practices.

Responsabilités

• Design, build, and deploy enterprise-scale AI applications using Python, .NET/C#, REST APIs, and microservices.
• Develop Generative AI, LLM, RAG, and Agentic AI solutions including prompting and tool calls.
• Build retrieval pipelines with embeddings, vector databases, and semantic/hybrid search.
• Leverage Azure OpenAI, Azure AI Search, Foundry, Services, Functions, and App Services.
• Integrate AI with enterprise apps, data platforms, and business workflows.
• Design secure, observable architectures with CI/CD, testing, monitoring, and logging.
• Ensure Responsible AI, governance, and security throughout the lifecycle.

Connaissances

Production-grade AI apps

Generative AI

LLMs

Prompt Engineering

RAG

Agentic AI

Multi-Agent Systems

Context engineering

LLM evaluation

Python

.NET

C#

REST APIs

Microservices

Azure OpenAI

Azure DevOps

Docker

CI/CD

MLOps

LangGraph

LangChain

Semantic Kernel

AutoGen

SQL/NoSQL

Embeddings

Vector databases

Distributed architectures

Outils

Azure OpenAI Service

Azure AI Search

Azure AI Foundry

Azure AI Services

Azure Functions

Azure App Services

Azure DevOps

Description du poste

Job Title: AI Solutions Engineer

Job Type: Full-Time

Work Mode: Hybrid (2/3 Days Office)

Location: Hyderabad, Bengaluru, Chennai, Pune

Experience: 6 - 12 Years

Working Hours: 2 - 11 PM

About the Role

We are seeking a highly skilled AI Solutions Engineer to architect, develop, and deploy enterprise-grade AI solutions using Generative AI, Large Language Models (LLMs), Python, .NET/C#, and Microsoft Azure Cloud as the primary technology stack. The ideal candidate will possess strong AI engineering expertise combined with modern software engineering capabilities to build scalable, secure, and production-ready AI applications.

This role requires hands‑on experience designing and implementing LLM-powered applications, RAG solutions, Agentic AI systems, and cloud‑native AI platforms. The successful candidate will be responsible for translating business requirements into enterprise AI architectures while owning the complete solution lifecycle from design and development through deployment, optimization, and production support.

Key Responsibilities

• Design, build, and deploy enterprise‑scale AI applications using Python, .NET, C#, REST APIs, and Microservices.
• Develop Generative AI, LLM, RAG, and Agentic AI solutions, including prompt engineering, tool/function calling, workflow orchestration, memory management, and multi‑agent architectures.
• Build and optimize retrieval pipelines encompassing document ingestion, chunking, embeddings, vector databases, semantic/hybrid search, reranking, and grounded response generation.
• Leverage Azure OpenAI, Azure AI Search, Azure AI Foundry, Azure AI Services, Azure Functions, and Azure App Services to deliver scalable cloud‑native AI solutions.
• Integrate AI capabilities with enterprise applications, APIs, databases, data platforms, and business workflows.
• Design secure, resilient, and observable architectures utilizing CI/CD, automated testing, monitoring, logging, and performance optimization.
• Troubleshoot and optimize AI applications across prompts, LLMs, retrieval systems, agents, APIs, backend services, and cloud infrastructure.
• Implement Responsible AI, security, governance, and engineering best practices throughout the AI solution lifecycle.

Required Skills

AI Engineering & GenAI

• Strong hands‑on experience building and deploying production‑grade AI applications.
• Deep expertise in Generative AI, Large Language Models (LLMs), Prompt Engineering, Retrieval‑Augmented Generation (RAG), and Agentic AI.
• Experience designing and implementing Multi‑Agent Systems and AI orchestration workflows.
• Strong understanding of LLM evaluation, context engineering, grounding techniques, hallucination mitigation, and Responsible AI practices.

Programming & Software Engineering

• Strong development experience with Python, .NET, and C#.
• Experience building enterprise applications using REST APIs, Microservices, and distributed architectures.
• Experience integrating AI services into enterprise‑grade software platforms.

Azure AI & Cloud

• Hands‑on experience with:
• Azure OpenAI Service
• Azure AI Search
• Azure AI Foundry
• Azure AI Services
• Azure Functions
• Azure App Services
• Azure DevOps
• Experience designing, deploying, and supporting AI workloads on Microsoft Azure Cloud.

LLM & AI Frameworks

• Hands‑on experience with LangGraph, LangChain, Semantic Kernel, AutoGen, or similar orchestration frameworks.
• Strong expertise in embeddings, vector databases, semantic search, hybrid retrieval, metadata filtering, reranking, and retrieval optimization.
• Experience building conversational AI, copilots, intelligent assistants, and enterprise AI solutions.

Platform Engineering

• Strong understanding of SQL/NoSQL databases, Docker, containerization, cloud‑native architectures, monitoring, and observability.
• Experience with CI/CD pipelines, automated testing, and production support.

Preferred Skills

• Experience with MLOps, LLMOps, AI model evaluation, monitoring, and governance frameworks.
• Experience building enterprise‑scale AI platforms with high availability, security, and scalability requirements.
• Exposure to modern front‑end technologies such as ReactJS or TypeScript is a plus.
• US Healthcare domain experience is desirable, including knowledge of Healthcare Payer/Provider ecosystems, Claims, Enrollment, Eligibility, Prior Authorization, Provider Data Management, FHIR/HL7 standards, and healthcare workflow modernization initiatives.