MUMBAI · FULLTIME
AI Engineer
Lacewing Technologies
Mumbai · onsite · Posted 33d ago
Sourced from
Undisclosed2–5 yrsfulltimeMumbai
About a minute. You'll make an account on the way through.
agent · working
- Read this posting0.5s
- Found the form on Naukri · 12 questions to answer1.1s
- Decided the answers for all of them2.5s
- Tailor your résumé to this role
- Waiting for you
Section · 01
About this role
What youll do
- Design and ship LLM agents end to end: retrieval, tools, evaluation, deployment
- Build RAG pipelines over messy real-world client documents
- Integrate with WhatsApp Business API, telephony providers and client CRMs
- Write evaluation harnesses so we know when quality regresses
- Own cost control - model routing, caching, rate limits
- Sit in client calls and translate a business problem into a system
What we need
- Python and/or TypeScript
- Hands-on with OpenAI / Anthropic / Gemini APIs
- Vector databases and embedding-based retrieval
- REST API design and webhook integration
- SQL and comfort with production databases
Nice to have
- LangGraph or similar agent frameworks
- Speech-to-text and TTS pipelines
- Indian-language NLP
Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.
Sourced from naukri
Section · 02
Skills
Retrieval Augmented Generationapisrest api designcachingai engineerNatural Language ProcessinggeminiVectorvector databasesRAG PipelinesLarge Language Models (LLMs)OpenAI SDKdeploymentPythonTypescriptSQLArtificial IntelligenceAnthropic SDK