Senior Backend Engineer - Speech Platform

Gohyred; Uttar Pradesh; On-site; INR 1,200,000 - 2,000,000; Full time

Job summary

Gohyred in Noida, Uttar Pradesh, is seeking a backend engineer to own the speech team’s engineering work, building ingestion, training infrastructure, real-time serving, and integration with our platform.

You will focus on backend systems, not model training; you’ll mine call archives, build real-time inference services with strict latency targets, and ensure scalable, cost-efficient operation across on-prem and cloud.

Qualifications

• 3-4 years building and operating production backend systems.
• Strong Java — you've owned services in production, not just contributed to them.
• Working Python — enough to build data pipelines and integrate with ML tooling
• Real-time or low-latency systems experience: streaming APIs, WebSocket or gRPC streaming
• Data pipelines at scale (Airflow, Dagster, Spark or equivalent)
• Docker and Kubernetes in production
• Cloud infrastructure (AWS/GCP/Azure)
• Comfortable debugging performance: profiling, latency percentiles, throughput under load
• Nice to have: Serving ML models in production (Triton, vLLM, TorchServe)
• Nice to have: Audio tooling — ffmpeg, sox, codecs, resampling
• Nice to have: Telephony — SIP, Asterisk/FreeSWITCH
• Nice to have: MLOps tooling: MLflow, Weights & Biases, DVC
• Nice to have: GPU-aware infrastructure work

Responsibilities

• Build the audio data pipeline: mine our call archive, transcode, resample, segment, deduplicate and quality-filter at scale
• Build and operate real-time inference services with hard latency targets, including streaming, cancellation and mid-utterance interruption
• Integrate speech services into our existing Java-based platform and telephony infrastructure
• Instrument the full latency budget end to end and find where the milliseconds go
• Stand up training infrastructure — GPU scheduling, checkpointing, experiment tracking, reproducibility
• Own compute cost and concurrency economics: how many simultaneous calls per GPU, and how to improve it
• Support on-premise deployment for clients who can't send data outside their network

Skills

Java production

Python data pipelines

Real-time / low-latency systems

WebSocket / gRPC streaming

Data pipelines at scale

Cloud-agnostic concepts

Tools

Docker

Kubernetes

Airflow

Dagster

Spark

AWS

GCP

Azure

Job description

Job Information

• Date Opened 28/09/2026
• Job Type Full time
• Industry Technology
• Work Experience 4-5 years
• City Noida
• Province Uttar Pradesh
• Country India
• Postal Code 201301

Job Description

About role:

You’ll be the engineering owner on the speech team, working alongside two ML engineers and building everything around the models — ingestion, training infrastructure, real-time serving, and the integration into our existing platform.

This is a backend engineering role. You don't need to train models. You need to build the systems that make trained models useful in production.

Responsibilities:

• Build the audio data pipeline: mine our call archive, transcode, resample, segment, deduplicate and quality-filter at scale
• Build and operate real-time inference services with hard latency targets, including streaming, cancellation and mid-utterance interruption
• Integrate speech services into our existing Java-based platform and telephony infrastructure
• Instrument the full latency budget end to end and find where the milliseconds go
• Stand up training infrastructure — GPU scheduling, checkpointing, experiment tracking, reproducibility
• Own compute cost and concurrency economics: how many simultaneous calls per GPU, and how to improve it
• Support on-premise deployment for clients who can't send data outside their network

Requirements

Must haves:

• 3-4 years building and operating production backend systems
• Strong Java — you've owned services in production, not just contributed to them
• Working Python — enough to build data pipelines and integrate with ML tooling
• Real-time or low-latency systems experience: streaming APIs, WebSocket or gRPC streaming, concurrency, backpressure
• Data pipelines at scale (Airflow, Dagster, Spark or equivalent)
• Docker and Kubernetes in production
• Cloud infrastructure (AWS/GCP/Azure)
• Comfortable debugging performance: profiling, latency percentiles, throughput under load

Nice to have:

• Serving ML models in production (Triton, vLLM, TorchServe)
• Audio tooling — ffmpeg, sox, codecs, resampling
• Telephony — SIP, Asterisk/FreeSWITCH, media servers, narrowband codecs
• MLOps tooling: MLflow, Weights & Biases, DVC
• GPU-aware infrastructure work