GenAI Engineer

Difinity Digital LLP; Ernakulam; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

Difinity Digital LLP is seeking a Senior AI Engineer with 4+ years of hands-on experience in designing, developing, and deploying AI-powered applications in Kerala, India. The role emphasizes RAG architectures, LLMs, vector databases, and scalable AI systems.

The candidate will lead AI development, mentor juniors, and collaborate across teams to deliver enterprise-grade chatbot and AI agent solutions using LangChain, LangSmith, and cloud deployments.

Qualifications

• 4+ years hands-on AI/ML development with Python.
• Experience with Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs).
• Hands-on experience with vector databases such as pgvector, Pinecone, ChromaDB, FAISS, Milvus, Weaviate or Qdrant.
• Experience with relational (PostgreSQL, MySQL) and NoSQL (MongoDB, Redis) databases.
• Experience building enterprise-grade AI chatbots and conversational AI applications.
• Proficiency with LangChain and LangGraph for AI orchestration.
• Experience with LangSmith or Langfuse for evaluation and observability.
• Web scraping using BeautifulSoup, Scrapy, Selenium or Playwright.
• Deploying AI apps to production using Docker and cloud platforms (AWS, Azure, GCP).
• Strong knowledge of FastAPI, REST APIs, PostgreSQL, Git and Linux.
• Ability to mentor junior engineers and provide technical leadership.

Responsibilities

• Design, develop, and deploy production-grade AI solutions using LLMs and RAG architectures.
• Build scalable chatbot and AI agent applications.
• Develop and optimize vector search, retrieval, and knowledge-base pipelines.
• Implement LLM evaluation, monitoring, and observability.
• Build and maintain web scraping and data ingestion pipelines.
• Guide and mentor team members, conduct technical reviews, and share best practices.
• Collaborate with cross-functional teams to deliver scalable, enterprise-grade AI solutions.

Skills

Python

LLMs

RAG

Vector DBs

Databases

LangChain

Web scraping

Docker

Cloud platforms

AI chatbots

Job description

4+years

Full-Time

We are looking for a Senior AI Engineer with 4+ years of experience in designing, developing, and deploying AI-powered applications.

Key Requirements

• 4+ years of hands‑on experience in AI/ML development using Python.
• Strong experience with Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), and AI Agents.
• Hands‑on experience with Vector Databases such as pgvector, Pinecone, ChromaDB, FAISS, Milvus, Weaviate, or Qdrant.
• Experience working with relational databases (PostgreSQL, MySQL) and NoSQL databases (MongoDB, Redis).
• Experience building enterprise‑grade AI chatbots and conversational AI applications.
• Proficiency with AI orchestration frameworks such as LangChain and LangGraph.
• Experience using LLM evaluation and observability frameworks such as LangSmith, Langfuse, or similar tools.
• Experience with web scraping using BeautifulSoup, Scrapy, Selenium, or Playwright.
• Experience deploying AI applications to production using Docker and cloud platforms (AWS, Azure, or GCP).
• Strong knowledge of FastAPI, REST APIs, PostgreSQL, Git, and Linux.
• Ability to mentor and guide junior AI engineers, conduct code reviews, and provide technical leadership to the team.

Responsibilities

• Design, develop, and deploy production‑ready AI solutions using LLMs and RAG architectures.
• Build scalable chatbot and AI agent applications.
• Develop and optimize vector search, retrieval, and knowledge base pipelines.
• Implement LLM evaluation, monitoring, and observability using frameworks such as LangSmith and Langfuse.
• Build and maintain web scraping and data ingestion pipelines.
• Guide and mentor team members, share best practices, conduct technical reviews, and support the team in delivering high‑quality AI solutions.
• Collaborate with cross‑functional teams to deliver scalable, enterprise‑grade AI solutions.