AI Application Engineer

We are looking for a technically adept and instructionally strong AI Developer with core

expertise in Python, Large Language Models (LLMs), prompt engineering, and vector search

frameworks such as FAISS, LlamaIndex, or RAG-based architectures. The ideal candidate

combines solid foundations in data science, statistics, and machine learning development with a

hands-on understanding of ML DevOps, model selection, and deployment pipelines.

3–4 years of experience in applied machine learning or AI development, including at least 1–2

years working with LLMs, prompt engineering, or vector search systems.

Core Skills Required:

• Python: Advanced-level expertise in scripting, data manipulation, and model development
• LLMs (Large Language Models): Practical experience with GPT, LLaMA, Mistral, or open-

source transformer models

• Prompt Engineering: Ability to design, optimize, and instruct on prompt patterns for various

use cases

• Vector Search & RAG: Understanding of feature vectors, nearest neighbor search, and

retrieval-augmented generation (RAG) using tools like FAISS, Pinecone, Chroma, or

Weaviate

• LlamaIndex: Experience building AI applications using LlamaIndex, including indexing

documents and building query pipelines

• Rack Knowledge: Familiarity with RACK architecture, model placement, and scaling on

distributed hardware

• ML / ML DevOps: Knowledge of full ML lifecycle including feature engineering, model

selection, training, and deployment

• Data Science & Statistics: Solid grounding in statistical modeling, hypothesis testing,

probability, and computing concepts

Responsibilities:

• Design and develop AI pipelines using LLMs and traditional ML models
• Build, fine-tune, and evaluate large language models for various NLP tasks
• Design prompts and RAG-based systems to optimize output relevance and factual grounding
• Implement and deploy vector search systems integrated with document knowledge bases
• Select appropriate models based on data and business requirements
• Perform data wrangling, feature extraction, and model training
• Develop training material, internal documentation, and course content (especially around

Python and AI development using LlamaIndex)

• Work with DevOps to deploy AI solutions efficiently using containers, CI/CD, and cloud

infrastructure

• Collaborate with data scientists and stakeholders to build scalable, interpretable solutions
• Maintain awareness of emerging tools and practices in AI and ML ecosystems

Preferred Tools & Stack:

• Languages: Python, SQL
• ML Frameworks: Scikit-learn, PyTorch, TensorFlow, Hugging Face Transformers
• Vector DBs: FAISS, Pinecone, Chroma, Weaviate
• RAG Tools: LlamaIndex, LangChain
• ML Ops: MLflow, DVC, Docker, Kubernetes, GitHub Actions
• Data Tools: Pandas, NumPy, Jupyter
• Visualization: Matplotlib, Seaborn, Streamlit
• Cloud: AWS/GCP/Azure (S3, Lambda, Vertex AI, SageMaker)

Ideal Candidate:

• Background in Data Science, Statistics, or Computing
• Passionate about emerging AI tech, LLMs, and real-world applications
• Demonstrates both hands-on coding skills and teaching/instructional abilities
• Capable of building reusable, explainable AI solutions

Location gurgaon sector 49