Inference Engineer – LLM & Speech AI
Read straight from Soket AI's careers page, verified 1d ago.Seekless can tailor your résumé to it.
Seekless can write your résumé for this posting first.
Before you apply
LocationBengaluru, India, Bengaluru, India
Typefull-time
SenioritySenior
DepartmentAI Infrastructure
Company size3+ people
PostedMay 10, 2026 · 6mo ago
Verified live1d ago
May no longer be actively hiring
Posted by the company on May 10, 2026Description is very short or shared across several roles
At a glanceSummarised by Seekless from the posting.
experience in building and optimizing high-performance inference systems for LLMs, Speech AI, and multimodal AI workloads
focus on low latency, high throughput, GPU efficiency, scalable serving infrastructure, distributed inference, and cost optimization
work at the intersection of systems engineering, deep learning infrastructure, distributed computing, and production AI deployment
collaborate with ML researchers, platform engineers, speech AI teams, and product engineering teams
Skills
LLMs
Speech AI
multimodal AI
GPU
distributed inference
About the role
We are looking for an experienced Inference Engineer to build and optimize high-performance inference systems for Large Language Models (LLMs), Speech AI systems, and multimodal AI workloads.
Responsibilities
You will work on deploying production-grade AI systems with a strong focus on:
•
low latency,
•
high throughput,
•
GPU efficiency,
•
scalable serving infrastructure,
•
distributed inference,
•
and cost optimization.
This role sits at the intersection of:
•
systems engineering,
•
deep learning infrastructure,
•
distributed computing,
•
and production AI deployment.
You will collaborate closely with:
•
ML researchers,
•
platform engineers,
•
speech AI teams,
•
and product engineering teams.