Conversational AI Engineer (LLM, RAG, Agentic Workflows)
Eighty Days · Mumbai
Job description
About the role
Eighty Days is building a map-based travel discovery platform that brings recommendations from social media, search and private conversations together. As a Conversational Agentic & RAG Engineer, you will build and own LLM-powered features for travel discovery, including conversational experiences, recommendations and reliable AI pipelines on a TypeScript backend, working closely with the founder.
Key responsibilities
- Build agentic, multi-step LLM workflows covering orchestration, tool calling, memory and multi-turn conversation state.
- Own the conversational AI end to end across in-app chat, from product requirement to production and iteration based on real user behaviour.
- Own retrieval quality for hybrid search and RAG systems, grounding answers in first-party data, and work on query understanding and entity resolution for location-aware search.
- Make LLM features reliable in production: structured outputs, streaming, fallbacks and routing across models by quality, latency and cost.
- Build async, event-driven pipelines that hold up under real user traffic.
- Build the evaluation and observability layer: tracing, eval datasets from real conversations, regression testing and metrics for relevance and groundedness.
- Optimise cost and latency across LLM workloads, and identify, design and architect the data each feature needs.
- Translate requirements and product insights into shipped features, collaborating closely with the founder, engineering and product.
Required profile
- 3-5 years of full-time software engineering experience.
- Shipped and owned a conversational, search or RAG feature used by real users at scale, not an internal tool or knowledge-base bot.
- Data-driven approach: defines success metrics, works with product analytics and uses funnel and conversion data.
- Nice to have: experience in a fast-paced AI-driven startup environment.
Required skills
- TypeScript and Node.js (NestJS preferred).
- LangChain or LangGraph for agentic workflows, and Langfuse for tracing and evaluation.
- Search with Elasticsearch/OpenSearch and vector search (Qdrant, Pinecone, etc.).
- Nice to have: LLM-as-judge setups, geo/places data, reranking, messaging APIs (WhatsApp Cloud, Instagram Graph), prompt caching, Model Context Protocol and multimodal understanding.
The position is on-site in Mumbai. ClanX is the recruitment partner helping Eighty Days hire the engineer.
Questions fréquentes
Why are you reporting this job?
Explore further
Salaries, guides and searches in India.
Salaries by job title
Apply in 30 seconds
Enter your email to apply. An account will be created automatically.
By continuing, you accept our terms of use.
Already have an account? Login
A question about this job?
Ask it here: you will get the full job summary by e-mail, right away.
Published 5 hours ago
Expires 1 month from now
9 views · 0 interested
Boost your chances
Upload your CV — we will match you with relevant openings.
Analyzing your CV...
Eighty Days
Mumbai
Related job offers
-
Senior Manager, Technology Strategy & Transformation (Tech Consulting, Banking)
EY Mumbai -
Assistant Vice President, Product Development (Data & AI)
statestreet Mumbai -
Senior Test Engineer - Banking & LOS
Indium Mumbai -
Développeur Front‑End UI/UX Scada (ReactJS) – GE Vernova
GE Vernova Paris -
Software Engineer - Backend Distributed Systems
salesforce