AIML Engineer\Senior AIML Engineer - Agentic AI & RAG Systems (Azure AI Foundry)

Chennai, Bangalore, Hyderabad

Job Description

Job Title : AIML Engineer - Agentic AI & RAG Systems (Azure AI Foundry)

Location : Chennai, Bangalore, Hyderabad

Who we are

Tiger Analytics is a global leader in AI and analytics, helping Fortune 1000 companies solve their toughest challenges. We offer full-stack AI and analytics services & solutions to empower businesses to achieve real outcomes and value at scale. We are on a mission to push the boundaries of what AI and analytics can do to help enterprises navigate uncertainty and move forward decisively. Our purpose is to provide certainty to shape a better tomorrow.

Our team of 4000+ technologists and consultants are based in the US, Canada, the UK, India, Singapore and Australia, working closely with clients across CPG, Retail, Insurance, BFS, Manufacturing, Life Sciences, and Healthcare. Many of our team leaders rank in Top 10 and 40 Under 40 lists, exemplifying our dedication to innovation and excellence.

We are a Great Place to Work-Certified™ (2022-24), recognized by analyst firms such as Forrester, Gartner, HFS, Everest, ISG and others. We have been ranked among the ‘Best’ and ‘Fastest Growing’ analytics firms lists by Inc., Financial Times, Economic Times and Analytics India Magazine

About the Role:

We are looking for a highly skilled AI Developer (3-8 yrs of experience) with strong experience in building and operating production-grade Generative AI systems using multi-agent architectures and advanced RAG pipelines on the Microsoft Azure ecosystem. This role involves designing intelligent AI workflows capable of reasoning, tool usage, enterprise integration, and scalable orchestration for high-volume business environments.

The ideal candidate should have hands-on expertise in developing agentic AI applications using Python, LangGraph, LangChain, and Azure AI services, with a strong focus on reliability, observability, security, and performance optimization.

Key Responsibilities:

Design and develop production-grade multi-agent AI systems using Python, LangGraph, and LangChain.
Build advanced RAG (Retrieval-Augmented Generation) pipelines including document ingestion, chunking, embeddings, vector indexing, semantic retrieval, and grounded response generation.
Develop AI agent workflows capable of reasoning, tool usage, task orchestration, and enterprise system integrations.
Implement scalable backend services and APIs to support AI-driven applications and workflows.
Build intelligent recommendation and matching systems leveraging structured and unstructured enterprise data.
Optimize AI systems for scalability, reliability, latency, and cost efficiency using caching, retries, rate limiting, and monitoring mechanisms.
Establish observability and evaluation frameworks to monitor hallucination rates, retrieval quality, tool-call accuracy, and model performance.
Collaborate with engineering, cloud, product, and business teams to deploy and productionize AI solutions.
Develop secure and auditable AI workflows aligned with enterprise governance and compliance standards.
Stay updated with advancements in Generative AI, Agentic AI, LLMs, and AI orchestration frameworks to drive innovation and platform improvements.

Required Qualifications:

5+ years of experience in software engineering, AI engineering, or related roles.
Strong proficiency in Python and backend development frameworks such as FastAPI.
Hands-on experience with LangGraph and/or LangChain.
Strong experience building RAG pipelines and working with vector databases/search systems.
Experience with Azure OpenAI, Azure AI Foundry, and Azure AI Search.
Expertise in Generative AI, LLMs, prompt engineering, embeddings, and semantic retrieval techniques.
Experience developing scalable APIs, microservices, and distributed AI systems.
Understanding of AI system observability, evaluation frameworks, and production monitoring.
Strong problem-solving skills with the ability to translate business requirements into scalable AI solutions.
Excellent communication and stakeholder management skills.

Preferred Qualifications:

Experience with AgentOps, LLMOps, or MLOps frameworks.
Exposure to observability and tracing tools such as LangSmith, MLflow, or OpenTelemetry.
Experience with Docker, Kubernetes, and cloud-native deployments.
Familiarity with recommendation engines, conversational AI, or voice AI systems.
Experience implementing caching, latency optimization, and token/cost optimization strategies for LLM applications.
Exposure to CI/CD pipelines and production AI deployment practices.
Experience working in enterprise-scale or high-volume AI environments.
Knowledge of GraphRAG, autonomous AI agents, or advanced orchestration architectures.

You are important to us, let’s stay connected!

Every individual comes with a different set of skills and qualities so even if you don’t tick all the boxes for the role today, we urge you to apply as there might be a suitable/unique role for you tomorrow. We are an equal opportunity employer. Our diverse and inclusive culture and values guide us to listen, trust, respect, and encourage people to grow the way they desire.

Note: The designation will be commensurate with expertise and experience. Compensation packages are among the best in the industry.

Additional Benefits: Health insurance (self & family), virtual wellness platform, and knowledge communities