AI Engineer / NLP, LLM & Agentic AI Specialist (Python)

Matrimony com; Chennai; On-site; INR 1,200,000 - 2,400,000; Full time

Job summary

Matrimony com in Chennai seeks an AI Engineer specializing in Python, NLP, LLMs, and agentic AI to design autonomous language-based solutions and integrate LLM APIs. You will build AI agents capable of reasoning, planning, and executing multi-step tasks, and collaborate with product teams to embed AI capabilities into user-facing applications.

The role offers a full-time opportunity for mid-level to senior engineers with strong Python and machine learning skills and a path to impact real-world

Qualifications

• Proficient in Python and NLP libraries (SpaCy, Transformers, NLTK, Gensim).
• Hands-on experience with LLM APIs and prompt-driven app development.
• Strong understanding of agentic AI concepts (planning, memory, tool use, multi-step reasoning).
• Experience with Hugging Face Transformers for training/fine-tuning.
• Knowledge of vector databases (FAISS, Weaviate, Pinecone) and RAG workflows.

Responsibilities

• Design and build NLP pipelines for classification, NER, summarization, sentiment analysis, and Q&A.
• Fine-tune/open-source LLMs using Transformers.
• Develop agentic AI workflows with autonomous decision-making and tool use.
• Build AI agents interacting with APIs, databases, and external tools.
• Preprocess large textual datasets using SpaCy, NLTK, or custom tokenizers.

Skills

Python

NLP

Transformers

SpaCy

NLTK

Gensim

LLM APIs

Agentic AI

REST APIs

Multi-step reasoning

Tools

Docker

Git

Flask/FastAPI

Job description

Job Title: AI Engineer / NLP, LLM & Agentic AI Specialist (Python)

Location: Chennai

Experience Level: Mid-Level / Senior

Employment Type: Full-Time

Job Summary

We are looking for a passionate AI Engineer with strong expertise in Python, Natural Language Processing (NLP), Large Language Models (LLMs), and emerging Agentic AI systems. You will design and build intelligent, autonomous language-based solutions, integrate LLM APIs, and develop AI agents capable of reasoning, planning, and executing multi-step tasks in real-world applications.

Key Responsibilities

Model Development, NLP & Agentic Systems

• Design and build NLP pipelines for tasks like classification, NER, summarization, sentiment analysis, and Q&A.
• Fine-tune and optimize open-source LLMs (e.g., BERT, GPT, T5) using Hugging Face Transformers.
• Develop agentic AI workflows that enable autonomous decision-making, multi-step reasoning, and tool usage.
• Build and orchestrate AI agents capable of interacting with APIs, databases, and external tools.
• Preprocess and structure large-scale textual datasets using SpaCy, NLTK, or custom tokenizers.

LLM Integration, Prompt Engineering & Agents

• Integrate LLM APIs (OpenAI, Claude, Cohere, Hugging Face) into real-time applications.
• Design, develop, and optimize prompt strategies and agent behaviors for reliability and performance.
• Build intelligent agents for use cases like chatbots, copilots, recommendation systems, and automation workflows.
• Implement tool-augmented agents and function-calling pipelines.
• Collaborate with product teams to embed LLMs and agentic systems into user-facing applications.

Deployment & Continuous Improvement

• Deploy models and agent systems as APIs using Flask, FastAPI, or Streamlit; containerize with Docker.
• Monitor model and agent performance, including reasoning accuracy and task completion rates.
• Implement evaluation pipelines for LLM and agent outputs.
• Continuously improve systems using user feedback and performance metrics.
• Stay updated with advancements in GenAI, agent frameworks, and NLP research.

Required Skills & Experience

• Proficient in Python and NLP libraries (SpaCy, Transformers, NLTK, Gensim).
• Hands-on experience with LLM APIs and prompt-driven application development.
• Strong understanding of agentic AI concepts (planning, memory, tool use, multi-step reasoning).
• Experience with Hugging Face Transformers for training/fine-tuning.
• Knowledge of NLP fundamentals: embeddings, attention, tokenization.
• Familiarity with vector databases like FAISS, Weaviate, or Pinecone (RAG systems).
• Experience building REST APIs and working with Docker and Git.

Preferred / Bonus Skills

• Experience with agent frameworks such as LangChain, LlamaIndex, AutoGen, CrewAI, or similar tools.
• Knowledge of RAG pipelines and agent-based retrieval workflows.
• Familiarity with evaluation metrics like BLEU, ROUGE, perplexity, cosine similarity.
• Exposure to cloud platforms (AWS, GCP, Azure).
• Experience in LLMOps, observability, and agent monitoring tools (PromptLayer, LangSmith, etc.).
• Contributions to NLP/GenAI open-source projects or research.