Senior MLOps Engineer Own model serving and evaluation infrastructure for the Dynmsol AI Platform. Lahore, PK (Hybrid)

Dynmsol; Lahore; On-site; PKR 1,800,000 - 3,200,000; Full time

Job summary

Dynmsol in Lahore is building the inference, evaluation, and monitoring infrastructure for its AI Platform. You will own the deployment, scaling, and reliability of model serving systems used by products and clients.

Collaborate with applied AI engineers, optimize throughput, latency, observability, and ensure robust evaluation pipelines. Requires Python and model-serving experience with vLLM, Triton, or similar.

Qualifications

• Proficiency in Python and building scalable software.
• Experience with model serving systems and ML infra is required.

Responsibilities

• Build, deploy, and operate inference, evaluation, and monitoring infrastructure for the Dynmsol AI Platform.
• Collaborate with applied AI engineers to ship client-facing features and ensure system reliability.

Skills

Python

Model serving

Tools

vLLM

Triton

Job description

Own model serving and evaluation infrastructure for the Dynmsol AI Platform.

You'll build and operate the inference, evaluation, and monitoring infrastructure that every AI product and client engagement runs on. This role sits at the center of the AI Platform team and works closely with applied AI engineers shipping client-facing features.

What we're looking for

• Python
• Model serving (vLLM, Triton, or similar)