Research Engineer - Agent Intelligence & Evaluation
About the job
- 3 to 5 years of experience in machine learning engineering, research engineering, or applied research.
- Strong Python skills and experience with modern machine learning tooling.
- Depth in at least two of speech and audio models, large language model agent systems, and evaluation or observability infrastructure.
- Experience shipping a non-trivial system where research was integrated with production.
- Ability to read research papers, identify when a benchmark measures the wrong thing, and translate ideas from Interspeech, ACL, or NeurIPS into systems operating on real traffic.
- Build evaluation infrastructure with audio-native metrics for barge-in, prosody, and turn-taking.
- Create adversarial datasets covering accents and edge cases.
- Develop large-language-model-as-judge rubrics for task success, tool-use correctness, and recovery.
- Build observability across the pipeline by tracing audio, speech-to-text, large language model reasoning, tool calls, and text-to-speech to a single conversation.
- Develop analysis and alerting that surfaces cascade failures.
- Mine production traces for failure patterns, generate targeted training or prompt data, validate fixes with adversarial replay, and guard against regressions.
- Safeguard sensitive company data against unauthorized access, use, or disclosure, and report suspected security incidents according to the organization's Information Security Management System policies and procedures.
- Real-time systems or telephony experience.
- Experience with reinforcement learning from human feedback, direct preference optimization, or synthetic data pipelines.
- Familiarity with enterprise deployment practices including SOC 2, personally identifiable information, and data residency.
- Publications are welcome but not required.
About the company
Ixigo is a travel booking platform focused on the Indian market, serving domestic and international travelers with flights, trains, buses, and hotels. The product helps users plan and book trips through a single interface that highlights fare drop alerts, cancellation protection, and personalized travel recommendations. Revenue comes from commissions on bookings made through the platform, plus advertising and premium services. What sets Ixigo apart is its large reach in India and its cross-modal search and analytics-enabled recommendations, designed to simplify travel planning and improve the user experience. The company’s goal is to grow total bookings and user satisfaction by making travel planning easier and more trustworthy through data-driven insights and convenience.
Company Size
501-1,000
Company Stage
IPO
Headquarters
Gurgaon, India
Founded
2007
Get referred to ixigo
See people who can refer or advise you
Simplify's Take
What believers are saying
- Q1 FY27 GTV hit ₹5,524 crore and PAT jumped 81% on August 6, 2026.
- Brevistay closed in June 2026, expanding ixigo's hotel supply and flexible-stay exposure.
- Selling 17.39% of Freshbus on August 13, 2026 freed capital for AI and hotels.
What critics are saying
- Karnataka GST demanded ₹23.8 crore on September 29, 2026, hitting bus margins.
- IRCTC and Indian Railways control train inventory, pricing rules, and booking economics.
- MakeMyTrip, Uber, and other super-apps can commoditize ixigo's booking layer by 2027.
What makes ixigo unique
- ixigo spans flights, trains, buses, and hotels across 150 million travelers.
- Uber launched train booking with ixigo on August 18, 2026, validating distribution leadership.
- Ixigo's AI-native Tara and ixigo NEXT deepen personalization and support at scale.
Help us improve and share your feedback! Did you find this helpful?
Benefits
- Flexible Work Hours