Skip to content

Software Engineer - 2 (Voicebot)

ExotelBengaluru, Karnataka, IndiaOn-Site

Estimated salary, not published by the employer: Est. ₹6.5–10 LPA

Needs a free Superjobs account. You'll finish on Exotel's site.

Skill score

Summary

This person builds, evaluates, and ships changes to Exotel's real-time voice AI bots, covering LLM and speech model evals, fine-tuning experiments, benchmarking, and production debugging of live calls. It suits an engineer with 2-4 years of software or ML experience who has shipped and owned production systems and wants to measure model quality rigorously before each change.

Function
Development
Estimated salary
Est. ₹6.5–10 LPA
Estimated for a mid-level role, ~2 yrs experience, India. Not published by the employer.
Work mode and location
On-Site, Bengaluru, Karnataka, India
Experience
2–4 yrs
Employment type
Full-time

Job description

Overview

The Voicebot team builds and operates Exotel's real-time voice AI product — production bots handling live phone conversations for enterprise customers.

We run real - time conversational pipelines end to end: speech recognition → LLM reasoning/orchestration → speech synthesis, with tool-calling for backend actions.

We evaluate and swap models constantly across providers, on cost, latency, and conversation quality not vibes.

We believe in measuring what matters: a good demo isn't the same as a good eval.

You'll be part of the team building and continuously improving Exotel's voicebot — from the model layer (fine-tuning, evals) to the live conversation experience (speech quality, latency, turn-taking). This is an engineering role first: you'll build, evaluate, and ship changes that directly improve call quality and business metrics in live customer deployments.

Roles and responsibilities

Build and maintain LLM/speech eval frameworks for the voicebot — task success, hallucination, instruction-following, WER/latency, barge-in and turn-taking quality — across model and prompt changes.

Run fine-tuning experiments (full FT, PEFT/LoRA/QLoRA) on open-weight models for domain specific voicebot tasks, and produce the evidence for when fine-tuning beats prompting.

Benchmark LLMs and ASR/TTS engines on cost, latency, and quality across providers and self hosted options and make a clear recommendation from the data.

Diagnose and fix real production conversation failures bad turn taking, misrecognition, latency spikes, prompt regressions using logs, traces, and eval data, not guesswork.

Ship changes into the live conversational pipeline, with instrumentation and alerting built in from day one.

Take ownership across the SDLC for your changes: design (with a senior engineer), eval design, deployment, and monitoring.

Skills required

Top skills

  • Python
  • LLM evaluation
  • Fine-tuning (LoRA/QLoRA)
  • Transformer architecture

All skills (8)

  • ASR/TTS evaluation
  • WER and latency metrics
  • Production systems
  • Real-time audio streaming
  • Agentic orchestration
  • RAG
  • Model self-hosting
  • AI observability

Qualifications

Independent execution. Given a scoped problem and an agreed approach, you take it to production on your own — build, eval, deploy, monitor — without needing to be unblocked daily.

Deep ownership of eval frameworks and working knowledge of associated services/infra. You go deep on the AI side of the product — models, evals, speech quality — and know enough about the surrounding services to trace a live problem across the pipeline and see it through.

Must-have

Solid grounding in ANNs and transformer architecture attention, tokenization, decoding strategies enough to reason about why a model behaves a certain way, not just call an API.

Hands-on experience with LLM evals: building or running eval harnesses, LLM-as judge setups, regression suites for prompt/model changes.

Hands-on experience with fine-tuning, including PEFT/LoRA/QLoRA — on at least one open weight model, for a real task (not just a tutorial).

Working knowledge of speech/ASR - TTS evaluation — WER, latency, diarization, common failure modes in real (noisy, accented, multilingual) audio.

Strong Python; comfortable reading/writing production code, not just notebooks.

2-4 years of software/ML engineering experience, with at least some of it in a production system (not purely research/academic).

A track record of shipping and owning your own changes in production you've been on the hook for something live.

Strong analytical rigor — you instinctively ask "how do we measure this" before shipping a change.

Nice to have

Experience with real-time audio/streaming systems and streaming vs. batch tradeoffs.

Experience with agentic orchestration and tool-calling patterns for LLMs.

Exposure to RAG patterns — embeddings, vector stores, retrieval strategies.

Familiarity with self-hosting/serving open-weight models.

Familiarity with observability for AI workloads — cost tracking, quality dashboards.

Experience with multi-tenant SaaS constraints (per-tenant config, isolation).

Prior experience specifically in voice AI / IVR / contact-center domains.

Other details

You own it. Build, eval, ship, monitor — and stay on the hook when it's running live. There's no separate "MLOps team" to hand off to.

You measure it. No model or prompt change ships without an eval story behind it.

You collaborate. You'll work closely with the voicebot architecture/product team and field delivery engineers shipping to enterprise customers. Good ideas win regardless of source.

You stay curious. New models and techniques land constantly — evaluating and benchmarking new options is part of the job, not a side project.

Company info

Exotel is the emerging market’s leading full-stack customer engagement platform and business-focused virtual telecom operator. Founded in 2011, our cloud-based product suite powers over 50 million daily engagements across voice, video, and messaging channels. Trusted by 6,000+ companies across 60+ countries—including India, Southeast Asia, the Middle East, and Africa—Exotel enables

More jobs at Exotel