AI Engineer

We are seeking a passionate and hands-on AI Engineer to join our growing Data & AI team. In this role, you will design, develop, and deploy next-generation LLM-powered chatbot, search, and automation solutions for enterprise use cases.

You will work with Google Cloud Vertex AI, Document AI, Dialogflow CX, LangChain, LangGraph, and vector databases to build intelligent conversational interfaces, RAG (Retrieval-Augmented Generation) systems, and AI-driven knowledge applications.

This is a highly technical and client-facing position ideal for someone who enjoys solving real-world problems using cutting-edge AI tools, frameworks, and Google Cloud technologies.

Key Responsibilities

Design, develop, and optimize AI chatbots using LLMs (e.g., Gemini, LLaMA, Claude, etc.)

Build semantic and enterprise search systems powered by RAG pipelines and vector databases

Orchestrate LLM workflows using LangChain and LangGraph

Develop backend services and APIs using FastAPI for AI-powered applications

Build interactive AI dashboards and demos using Streamlit for rapid prototyping and client presentations

Implement prompt engineering, model tuning, and evaluation for various business domains

Integrate and deploy solutions leveraging Google Cloud Vertex AI, Document AI, Dialogflow CX, BigQuery, and Cloud Functions

Fine-tune foundation models and implement domain-specific customizations where needed

Contribute to best practices, documentation, CI/CD pipelines, and code reviews

Collaborate closely with Data Engineers and Solution Architects to deliver scalable AI systems

Essential Skills & Experience

3+ years of experience as an AI/ML Engineer or Software Engineer in AI-focused project

Strong understanding of LLMs, transformers, and conversational AI architectures

Proven experience with LangChain, LangGraph, or similar LLM orchestration frameworks

Hands-on experience with FastAPI (or Flask) for backend service development

Experience with Streamlit for building interactive AI demos or internal tooling

Familiarity with Prompt Engineering, RAG pipelines, and LLM evaluation methodologies

Proficient in vector search, embeddings, and similarity-based retrieval (e.g., FAISS, Weaviate, Pinecone, Milvus)

Working knowledge of Dialogflow CX, Vertex AI, and Document AI

Strong foundation in software engineering Git, CI/CD, REST APIs, testing

Bonus Skills (Nice to Have)

Experience with data engineering tools (ETL, Airflow, dbt, BigQuery, or Snowflake)

Experience integrating external data sources, web crawlers, or knowledge bases

Familiarity with data lake/warehouse architecture and data pipeline design

Cloud infrastructure knowledge: GCP, AWS, or Azure

Experience fine-tuning open-source LLMs (LLaMA, Mistral, Falcon, etc.)

Understanding of LLM safety, reliability, and cost-performance optimization

Exposure to frontend frameworks (React, Next.js) for chatbot UI integration