AHMEDABAD · FULLTIME

AI ML Python Developer

Arrow Electronics India Private Limited

Ahmedabad · onsite · Posted 9d ago

Sourced from Foundit

Not disclosedFresherfulltimeAhmedabad

Your match

Section · 01

About this role

Job Description:

Design and develop scalable backend services and REST APIs using Python, FastAPI/Flask/Django.
Build and integrate Generative AI/LLM-based applications, including RAG, AI agents, embeddings, and tool/function calling.
Work with Azure OpenAI and other LLM providers.
Use AI frameworks such as LangChain, LlamaIndex, LangGraph, or similar.
Implement LiteLLM for LLM gateway, routing, fallback, and usage/cost management.
Implement rate limiting, throttling, caching, retries, and API quotas for scalable services.
Use Langfuse for LLM observability, tracing, prompt management, token/cost tracking, and evaluation.
Design and work with PostgreSQL/MySQL, MongoDB, and Redis.
Deploy and manage applications using Microsoft Azure, Docker, and CI/CD.
Develop unit/integration tests, troubleshoot production issues, and optimize performance and cost.
Participate in system design, code reviews, and technical architecture discussions.
Required
5-7 years of software development experience with strong Python and backend development skills and hands-on experience in Generative AI/LLM applications.
Strong understanding of REST APIs, microservices, RAG, embeddings, vector databases, prompt engineering, AI agents, rate limiting, and distributed systems.
Hands-on experience with Azure OpenAI, LiteLLM, and Langfuse is preferred, along with exposure to LangChain/LlamaIndex/LangGraph or similar AI frameworks.
Experience with Microsoft Azure, Docker, CI/CD, databases, Redis, API security, and cloud-native application development is required.
Strong problem-solving, communication, ownership, and ability to build production-grade AI solutions are essential.

Sourced from foundit

Let the agent run this one for you.

Tailored resume, auto-apply, and referral lookup — in under 2 minutes.

Section · 02

Skills

DockerRetrieval Augmented GenerationPrompt EngineeringPostgresqlDistributed Systemsapi securityredisDjango FrameworkLangfuseAzure OpenAIvector databasesEmbeddingsLiteLLMcloud-native application developmentLLM ApplicationsFlask FrameworkRate limitingPythonMongoDBMySQLREST APIMicroservicesMicrosoft AzureLanggraphLangchainAgentic AiGenerative AiLlamaindexCi/CdFastAPI

Job search guides

Job Description:

Design and develop scalable backend services and REST APIs using Python, FastAPI/Flask/Django.

Build and integrate Generative AI/LLM-based applications, including RAG, AI agents, embeddings, and tool/function calling.

Work with Azure OpenAI and other LLM providers.

Use AI frameworks such as LangChain, LlamaIndex, LangGraph, or similar.

Implement LiteLLM for LLM gateway, routing, fallback, and usage/cost management.

Implement rate limiting, throttling, caching, retries, and API quotas for scalable services.

Use Langfuse for LLM observability, tracing, prompt management, token/cost tracking, and evaluation.

Design and work with PostgreSQL/MySQL, MongoDB, and Redis.

Deploy and manage applications using Microsoft Azure, Docker, and CI/CD.

Develop unit/integration tests, troubleshoot production issues, and optimize performance and cost.

Participate in system design, code reviews, and technical architecture discussions.

Required

5-7 years of software development experience with strong Python and backend development skills and hands-on experience in Generative AI/LLM applications.

Strong understanding of REST APIs, microservices, RAG, embeddings, vector databases, prompt engineering, AI agents, rate limiting, and distributed systems.

Hands-on experience with Azure OpenAI, LiteLLM, and Langfuse is preferred, along with exposure to LangChain/LlamaIndex/LangGraph or similar AI frameworks.

Experience with Microsoft Azure, Docker, CI/CD, databases, Redis, API security, and cloud-native application development is required.

Strong problem-solving, communication, ownership, and ability to build production-grade AI solutions are essential.