AI Engineer

Comviva · Gurgaon

  • Experience3–4 yrs
  • SalaryNot disclosed
  • Work modeonsite
  • Posted1 Oct 2026
Apply for this job

About Comviva

Comviva is hiring in Gurgaon in technology software. This role looks for around 3+ years of experience.

Skills

  • LLM-based conversational AI systems
  • Python
  • FastAPI
  • Flask
  • Speech-to-Text
  • Text-to-Speech
  • RAG pipelines
  • Embeddings
  • Vector search
  • Conversational AI workflows

The role

A generative AI engineer at a financial technology company designs LLM-based conversational AI systems and builds Python backend services using FastAPI or Flask for chatbots, assistants, and agents. The role develops RAG pipelines and integrates Speech-to-Text, while applying conversational AI workflows and real-time interaction systems.

Full job description

About YABX

Yabx is a global FinTech venture of Mahindra Comviva, focused on simplifying financial access for the 2+ billion under-banked population across emerging markets in Africa, Asia, and Latin America.

We leverage technology and advanced analytics to reduce the cost of delivering financial services by partnering with leading Telecom Operators, Banks, MFIs, Credit Bureaus, Mobile Financial Providers, and handset vendors.

Yabx was incubated by Mahindra Comviva and operates across The Hague, New Delhi, and Nairobi, bringing together a team of industry experts and entrepreneurs with global experience. Our mission is to build world-class, innovative products that meaningfully improve people’s lives.

Key Responsibilities

Design, build, and deploy LLM-powered applications including chatbots, assistants, and AI agents Develop scalable backend services and APIs using Python, FastAPI, or Flask Implement RAG pipelines using embeddings, vector databases, and retrieval systems Integrate Speech-to-Text (STT) and Text-to-Speech (TTS) technologies Design conversation memory, context management, and session-handling mechanisms Build real-time AI interaction systems using WebSockets or streaming APIs Monitor, evaluate, and improve AI systems using prompt management and observability tools Ensure systems are production-ready, scalable, and reliable

Required Skills

Hands-on experience building LLM-based conversational AI systems (chatbots, assistants, or agents) Strong proficiency in Python Experience with FastAPI or Flask for backend development Experience integrating Speech-to-Text and Text-to-Speech services (e.g., Deepgram, ElevenLabs, or similar) Solid understanding of RAG pipelines, embeddings, and vector search Knowledge of conversational AI workflows including memory, context, and session management

Nice to Have

Familiarity with telephony systems such as SIP, RTP, VoIP, or WebRTC Experience with LLM observability tools like Langfuse, Phoenix, or similar platforms Experience building real-time systems using WebSockets (WSS)