
ti Steps•1h ago
Naukri
Ai Ml Engineer
Chennai(Thousand Lights)
Full Time
Mid Level
N/A
N/A
N/A
Full Job Description
AI/ML Engineer | Chennai
Location: Chennai, India
Employment Type: Full-Time
Experience Required: 2 - 4 Years
We are seeking a motivated AI/ML Engineer to develop scalable AI platforms, specializing in Large Language Models (LLMs), Generative AI, Retrieval-Augmented Generation (RAG) pipelines, and Agentic AI systems. This role requires strong Python-based AI development skills and experience deploying production-ready AI solutions with modern frameworks and vector databases. You will contribute to building intelligent enterprise solutions such as AI-powered job description creators, resume parsers, candidate scoring engines, and chatbots.
Key Responsibilities
AI & LLM Development
- Design, develop, and optimize LLM-powered applications using LangChain and LangGraph.
- Build and maintain RAG pipelines utilizing vector databases.
- Implement Agentic AI workflows and multi-agent systems.
- Integrate and optimize transformer-based models for NLP tasks.
- Develop prompt engineering strategies and evaluation pipelines for Generative AI systems.
Backend & API Development
- Develop and deploy scalable APIs using FastAPI.
- Integrate AI models into backend systems, ensuring high performance and reliability.
- Implement caching strategies with Redis for latency optimization.
- Build microservices-based AI architectures.
Data Engineering & Model Development
- Train and fine-tune ML/DL models using PyTorch, TensorFlow, and Scikit-learn.
- Implement NLP pipelines including tokenization, embeddings, semantic search, and text analysis.
- Perform feature engineering, data preprocessing, and model evaluation.
- Work with both structured and unstructured data.
Vector Search & Databases
- Implement semantic retrieval using Vector Databases such as MongoDB Atlas, FAISS, Pinecone, Weaviate, Chroma, and Milvus.
- Optimize similarity search, hybrid retrieval, and ranking systems.
- Design efficient embedding pipelines.
Deployment & Optimization
- Deploy AI services on cloud platforms (AWS/GCP/Azure).
- Containerize applications using Docker.
- Optimize latency through Redis caching and query tuning.
- Monitor AI system performance and enhance scalability.
Required Skills
Programming & Backend
- Strong proficiency in Python
- FastAPI
- REST API development
- SQL (MySQL/PostgreSQL)
AI / ML / DL
- Machine Learning & Deep Learning
- Transformers & LLMs
- Generative AI
- RAG Architecture
- LangChain
- LangGraph
- Agentic AI
- Model evaluation techniques
NLP & Search
- NLP (NLTK, Text Processing)
- Embeddings (OpenAI, HuggingFace, Vertex AI, etc.)
- Semantic search & hybrid search
- Prompt engineering
Databases & Tools
- Redis
- Vector Databases
- MongoDB
- Git
- Docker
Good to Have
- Experience with MCP (Model Context Protocol)
- Experience with real-time AI systems
- Experience with CI/CD pipelines
- Knowledge of MLOps best practices
Preferred Qualifications
- 2–4 years of hands-on experience in AI/ML development.
- Experience building production-grade AI systems.
- Strong problem-solving and system design skills.
- Ability to thrive in a fast-paced startup environment.
- Excellent communication skills.
Company
ti Steps
Chennai(Thousand Lights)
Posted on Naukri