Posted 02 July, 2026
AI Engineer
NR Consulting - India
Mumbai, Maharashtra, IN
Full Time
Reference: 26-02476-2220-1
Title: AI Engineer
Location: Mumbai
Exp: 3-5 yrs
Job Description:
Key Responsibilities :
" Design end-to-end LLM applications with WebSocket and FastAPI
" Develop LLM workflows , orchestration, multi-agent patterns, prompt engineering and RAG pipelines
" Work with ASR/TTS/VAD tools (Elevenlabs, Azure Speech, ONNX Runtime)
" Build scalable data pipelines (Python, Cloud Run, Cloud Functions, Pub/Sub)
" Integrate LLM applications with APIs and enterprise data sources
" Implement structured outputs, tool-calling, and function-execution flows
" Deploy, monitor, and optimize AI services on GCP/Azure
" Conduct LLM performance testing (latency, reliability, grounding, bias checks)
" Containerize and automate workflows using Docker & GitHub
" Ensure model safety, guardrails, hallucination checks, and output quality benchmarking
Required Skills:
" Python (advanced)
" LLMs (GPT, Gemini, LLaMA), RAG, vector DBs
" Speech AI (ASR, TTS, VAD)
" Build and optimize ML/DL models
" Cloud platforms (GCP preferred)
" Data engineering & pipeline development
" MLOps: Docker, CI/CD, model/prompt versioning
Location: Mumbai
Exp: 3-5 yrs
Job Description:
Key Responsibilities :
" Design end-to-end LLM applications with WebSocket and FastAPI
" Develop LLM workflows , orchestration, multi-agent patterns, prompt engineering and RAG pipelines
" Work with ASR/TTS/VAD tools (Elevenlabs, Azure Speech, ONNX Runtime)
" Build scalable data pipelines (Python, Cloud Run, Cloud Functions, Pub/Sub)
" Integrate LLM applications with APIs and enterprise data sources
" Implement structured outputs, tool-calling, and function-execution flows
" Deploy, monitor, and optimize AI services on GCP/Azure
" Conduct LLM performance testing (latency, reliability, grounding, bias checks)
" Containerize and automate workflows using Docker & GitHub
" Ensure model safety, guardrails, hallucination checks, and output quality benchmarking
Required Skills:
" Python (advanced)
" LLMs (GPT, Gemini, LLaMA), RAG, vector DBs
" Speech AI (ASR, TTS, VAD)
" Build and optimize ML/DL models
" Cloud platforms (GCP preferred)
" Data engineering & pipeline development
" MLOps: Docker, CI/CD, model/prompt versioning
