MLOps Engineer

GyanSys Inc.; Bengaluru; Hybrid; INR 1,400,000 - 2,100,000; Full time

Job summary

GyanSys Inc. in Bengaluru seeks a hands-on AI Deployment Engineer responsible for ML engineering, model deployment, governance and observability across cloud, on-premises, hybrid and air-gapped environments.

You will own the complete lifecycle of DL models, LLMs and SLMs, build MLOps/LLMOps pipelines, optimize performance and cost, and implement governance, monitoring and secure access with Keycloak.

Qualifications

• 3–5 years in MLOps, LLMOps, ML Engineering, or AI Engineering.
• Hands-on experience with Databricks and/or Azure ML.
• Experience with Deep Learning, LLMs, SLMs, RAG, and Hugging Face.
• Experience deploying models built using PyTorch and TensorFlow.
• Strong GPU knowledge including NVIDIA GPUs, CUDA, multi-GPU deployments, and inference optimization.

Responsibilities

• Build and manage MLOps and LLMOps pipelines.
• Deploy, host, and scale Deep Learning models, LLMs, and Inference optimisation.
• Manage end-to-end model lifecycle including versioning, deployment, rollout, rollback, and retirement.
• Host models on Databricks, Kubernetes, OpenShift, and GPU-based infrastructure.
• Implement model governance, lineage, approval workflows, and compliance controls.
• Build model monitoring, observability, tracing, logging, and drift detection capabilities.
• Optimize model performance, latency, throughput, GPU utilization, and cost.
• Support cloud, on-premises, hybrid, and air-gapped environments.
• Experience with Vector Databases (Pinecone, Chroma, FAISS, Milvus, Azure AI Search).
• REST APIs, WebSockets, Streaming HTTP.
• Experience with MLflow, OpenTelemetry, LangFuse, Splunk, and Grafana/ELK.
• Experience across Cloud, On-Premises, Hybrid, and Air-Gapped environments.
• Experience with Auth setup like Keycloak

Skills

MLOps

LLMOps

ML Engineering

AI Engineering

Databricks

Azure ML

Deep Learning

LLMs

SLMs

RAG

Hugging Face

PyTorch

TensorFlow

GPU Infrastructure

NVIDIA GPUs

CUDA

Model Registry

Model Governance

Model Monitoring

Drift Detection

AI Observability

Vector Databases

Pinecone

Chroma

FAISS

Milvus

Azure AI Search

REST APIs

WebSockets

Streaming HTTP

MLflow

OpenTelemetry

LangFuse

Splunk

Grafana

ELK

Keycloak

Tools

Kubernetes

OpenShift

GPU infrastructure

Job description

Location: Bangalore (Working from Office / Hybrid)

Job Description

We are seeking a hands-on AI Deployment Engineer specializing in ML Engineering, Model Deployment, Model Governance, and Model Observability. The engineer will own the complete lifecycle of Deep Learning models, LLMs, and SLMs across cloud, on-premises, hybrid, and air-gapped environments.

Scope of Work

Build and manage MLOps and LLMOps pipelines.

Deploy, host, and scale Deep Learning models, LLMs, and SLMs and Inference optimisation

Manage end-to-end model lifecycle including versioning, deployment, rollout, rollback, and retirement.

Host models on Databricks, Kubernetes, OpenShift, and GPU-based infrastructure.

Implement model governance, lineage, approval workflows, and compliance controls.

Build model monitoring, observability, tracing, logging, and drift detection capabilities.

Optimize model performance, latency, throughput, GPU utilization, and cost.

Support cloud, on-premises, hybrid, and air-gapped environments.

Must-Have Skills

• 3–5 years in MLOps, LLMOps, ML Engineering, or AI Engineering.
• Hands-on experience with Databricks and/or Azure ML.
• Experience with Deep Learning, LLMs, SLMs, RAG, and Hugging Face.
• Experience deploying models built using PyTorch and TensorFlow.
• Databricks
• GPU Infrastructure

Experience with:

• vLLM
• Triton Inference Server
• Ray Serve
• SGLang
• Databricks Model Serving

Strong GPU knowledge including NVIDIA GPUs, CUDA, multi-GPU deployments, and inference optimization.

Experience in Model Registry, Model Governance, Model Monitoring, Drift Detection, and AI Observability.

Experience with Vector Databases (Pinecone, Chroma, FAISS, Milvus, Azure AI Search).

REST APIs, WebSockets, Streaming HTTP.

Experience with MLflow, OpenTelemetry, LangFuse, Splunk, and Grafana/ELK.

Experience across Cloud, On-Premises, Hybrid, and Air-Gapped environments.

Experience with Auth setup like Keycloak

Good-to-Have Skills

• Fine-tuning and model optimization
• Model Governance & Security
• Experience with Llama, Mistral, DeepSeek, Qwen, Phi, and Gemma models