Research Engineer - Agent Intelligence & Evaluation New

NetVerks Inc.; Delhi; Sur place; INR 1 800 000 - 3 000 000; Plein temps

Avantages offerts par ce poste

Real equity

Autonomy over tooling

Support to publish

Résumé du poste

NetVerks Inc. seeks a ML fellowship engineer to own the intelligence layer for self-healing voice agents used in ixigo's enterprise support.

You will build evaluation infrastructure, observability across the audio pipeline, and self-improvement loops; collaborate with teams to ensure governance and security of enterprise data. Candidates with 3–5 years in ML and strong Python will thrive in this role.

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.

Responsabilités

• Own evaluation infrastructure for audio-native metrics and adversarial datasets.
• Maintain observability across the pipeline, tracing audio, STT, LLM reasoning, tool calls, and TTS.
• Develop self-improvement systems: mine production traces, generate training data, and validate fixes.

Connaissances

Python

ML tooling

Speech and audio models

LLM agent systems

Eval/Observability infra

Description du poste

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…

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 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.

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.

Requirements

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.