Senior Back-end AI Engineer

Sumeru Global Technologies Private Limited

United States

2 months ago

Apply on indeed.com

Prepare application

Role details

Contract type

Permanent contract

Employment type

Full-time (> 32 hours)

Experience level

Expert

Experience required

2 years minimum

Compensation

$145,600.0 - $166,400.0

Working hours

Regular working hours

Job source

indeed.com

Tech stack

Java (Programming Language) .NET Framework Application Programming Interfaces (APIs) Artificial Intelligence Microsoft Azure Continuous Integration Python (Programming Language) Node.Js Role-Based Access Control Enterprise Application Integration Data Logging Chatbots

+9 more

Large Language Models Generative AI Backend AI Platforms Kubernetes Low Latency Front End Software Development Docker Microservices

Job description

Build backend services for conversation orchestration, session handling, AI response generation, STT/TTS integration, and workflow execution.
Integrate with OpenAI, Azure OpenAI/Azure AI, Claude, and client-approved enterprise model gateways. Implement prompt workflows, model routing, tool/function calling, guardrails, fallback handling, and response streaming.
Optimize latency, token usage, response consistency, and operational cost. Build secure, auditable APIs with logging, monitoring, RBAC, and enterprise integration patterns.
Collaborate with frontend, data/RAG, client architects, and SMEs during implementation, demos, and UAT.

Requirements

Do you have experience in Production systems?, * Strong backend development using Python, Node.js, Java, or .NET. Experience building production APIs, microservices, or platform services.

Minimum 2 years hands-on AI implementation experience.
Experience with OpenAI, Azure OpenAI, Azure AI, Claude, Gemini, or similar models.
Experience with STT/TTS, conversational AI, prompt orchestration, tool calling, or agentic workflows.
Understanding of hallucination controls, PII handling, token management, latency, and model behavior.
BFSI, banking, insurance, capital markets, payments, or regulated enterprise experience.
Client implementation experience.

Preferred Skills:

Azure AI Speech, OpenAI Realtime APIs, Semantic Kernel, LangChain, LlamaIndex, AutoGen, or similar frameworks. Experience with shared libraries, CI/CD, observability, and cloud deployment.
Docker, Kubernetes, Azure App Service, Azure Container Apps, or equivalent., * How many years of hands-on experience do you have building Generative AI / LLM-based applications in production?
Which AI platforms have you integrated with in production?
Have you built production-grade conversational AI, AI assistants, agentic workflows, or tool-calling applications?
How many years of backend development experience do you have using Python, Node.js, Java, or .NET?