Research Engineer - Agent Intelligence & Evaluation

Ixigo; New Delhi; On-site; INR 1,200,000 - 1,800,000; Full time

Benefits offered by this job

Equity

Autonomy over tooling

Support to publish

Job summary

Ixigo is building self-healing voice agents for enterprise customer support, owning the intelligence layer for evaluations, observability, and feedback loops that enable agents to fix themselves.

The fellowship role focuses on evaluation infrastructure, pipeline observability, and self-improvement systems, with a chance to impact production-grade AI that handles real traffic in enterprise environments.

Qualifications

• 3 to 5 years in ML engineering, research engineering, or applied research
• Strong Python and modern ML tooling
• Depth in at least two of: speech and audio models, LLM agent systems, and eval or observability infrastructure

Responsibilities

• Evaluation infrastructure: audio-native metrics, adversarial datasets, LLM-as-judge rubrics.
• Observability across the pipeline: tracing audio, STT, LLM reasoning, tool calls, and TTS.
• Self-improvement systems: mine production traces, generate training data, validate fixes with adversarial replay.

Skills

Python

ML tooling

Speech models

LLM agent systems

Eval/instrumentation

Tools

Observability tools

Audio processing tools

LLM frameworks

Job description

• Full-time

Company Description

We’re building self-healing voice agents for enterprise customer support within ixigo. The system has to know when it’s failing, why it’s failing, and how to fix itself before a human notices. This fellowship sits at the intelligence layer behind that work.

Job Description

Voice agents fail in ways traditional software doesn't. ASR confidence drops on an accent and a tool call misfires. Latency breaks turn-taking and the LLM hallucinates a policy. A model swap silently regresses production and nobody catches it for a week.

We're building self-healing voice agents for enterprise customer support. This role owns the intelligence layer: the evals that catch failures before shipping, the observability that traces them across the pipeline, and the feedback loops that let agents fix themselves

What you’ll own

• Evaluation infrastructure. Audio-native metrics for barge-in, prosody, and turn-taking. Adversarial datasets across accents and edge cases. LLM-as-judge rubrics for task success, tool-use correctness, and recovery.
• Observability across the pipeline. Tracing that correlates audio, STT, LLM reasoning, tool calls, and TTS to a single conversation. Analysis and alerting that surfaces cascade failures instead of hiding them.
• Self-improvement systems. Mine production traces for failure patterns, generate targeted training or prompt data, validate fixes with adversarial replay, and guardrail against regressions.

Qualifications

Who we're looking for

• 3 to 5 years in ML engineering, research engineering, or applied research. Strong Python and modern ML tooling. Depth in at least two of: speech and audio models, LLM agent systems, and eval or observability infrastructure.
• You’ve shipped something non-trivial where research met production. You read papers, spot when a benchmark measures the wrong thing, and translate ideas from Interspeech, ACL, or NeurIPS into systems that run on real traffic. Publications welcome, not required.

Nice to have

• Real-time systems or telephony experience. Work on RLHF, DPO, or synthetic data pipelines. Familiarity with enterprise deployment (SOC 2, PII, data residency).

• What you’ll get: Senior seat on a small team where research and production aren't separate orgs. Real enterprise conversation data under proper governance. Meaningful equity, autonomy over tooling, and support to publish.

Additional Information

Candidates are responsible for safeguarding sensitive company data against unauthorized access, use, or disclosure, and for reporting any suspected security incidents in line with the organization's ISMS (Information Security Management System) policies and procedures.