Back to all jobs
Actively HiringOn-Site (HITEC City)

AI / LLM Infrastructure Engineer

Atlas AnalyticsHyderabad, Telangana
AA
CTC / Compensation₹28L - ₹45L + ESOPs
Experience2-4 years
Start DateImmediately
Apply By15 Oct '26
Posted 2 days ago142 ApplicantsFull Time

Key Skills Required

PyTorchPythonFastAPIvLLMTritonCUDALangChain

About the Role

Scale our video and diffusion inference pipelines to support real-time video personalization for millions of customer interactions every month.

Day-to-day Responsibilities

1.Optimize generative diffusion models for low-latency GPU inference using TensorRT and vLLM.
2.Build scalable async queue workers managing heavy video rendering jobs across multi-node GPU clusters.
3.Implement fine-tuning and LoRA pipelines tailored to enterprise voice and branding profiles.
4.Monitor GPU memory utilization, throughput metrics, and inference latency SLOs.

Requirements & Eligibility

2+ years of hands-on experience deploying PyTorch or TensorFlow models to production.
Deep understanding of Transformer architectures, attention mechanisms, and diffusion generation.
Proficiency with Python, FastAPI, Docker, and Linux GPU drivers (CUDA).

Hiring Process & Rounds

1Round 1: 30-min AI Lead Screening
2Round 2: Machine Learning & Python Systems Design
3Round 3: Live Inference Optimization Task
4Round 4: CTO Fit & Offer

About Atlas Analytics

Website

Atlas Analytics combines diffusion video models with real-time analytics to generate personalized dynamic video assets for product marketing campaigns.

14+Active openings
11-50Team size
< 7 DaysAvg. response
INTERVIEW PREP

Practice Atlas Analytics Mock Interview

Take a 15-minute voice AI interview using verified technical questions for this role.

Start Free Practice
RESUME SCORE

Check Resume Match

Check your resume compatibility score against this job description before applying.

Scan Resume