Ai Ml Engineer

Dess Technologies; Mumbai; On-site; INR 1,200,000 - 1,700,000; Full time

Job summary

Dess Technologies in Mumbai is seeking a skilled Python developer to design and build scalable backend services and APIs, leveraging AI/ML capabilities and LLMs.

Ideal candidates have 4+ years of Python experience, hands-on expertise with FastAPI, REST, and cloud platforms, and the ability to deploy production-grade AI-driven applications using OpenAI models and vector databases.

Qualifications

• 4+ years in Python backend and API development.
• Experience with FastAPI, REST APIs, and async programming.
• Hands-on with OpenAI models and open-source LLMs.
• Experience with RAG systems and vector databases.

Responsibilities

• Develop scalable backend services and APIs.
• Work with Generative AI and LLMs in production.
• Integrate OpenAI models and open-source LLMs.
• Design prompt strategies and optimize LLM outputs.
• Build and maintain RAG pipelines with vector DBs.
• Implement semantic search and vector embeddings.

Skills

Python development

API design

AI/ML concepts

LLMs

Cloud (Azure/AWS)

Git

SQL

FastAPI

REST APIs

Asynchronous programming

Tools

FAISS

Qdrant

Pinecone

ChromaDB

Job description

Experience: Total 4 plus years of experience, relevant experience in AI, Machine Learning, Python, API, Azure/AWS, LLMs, SQL, GIT

Role & responsibilities

• Strong Python Development Experience
• 4 years of experience in Python development with expertise in designing scalable backend services, APIs, and AI-driven applications.
• Experience with FastAPI, REST APIs, asynchronous programming, and production grade application development. Generative AI & Large Language Models (LLMs)
• Hands-on experience working with OpenAI models (GPT-4o, GPT-4 Turbo, Azure OpenAI) and open-source LLMs such as Llama, Mistral, Gemma, or Qwen.
• Ability to design prompt engineering strategies and optimize LLM outputs for enterprise use cases. Retrieval-Augmented Generation (RAG) Systems
• Experience building and maintaining RAG pipelines using vector databases such as FAISS, Qdrant, Pinecone, or ChromaDB.
• Strong understanding of document chunking, embedding generation, retrieval strategies, reranking, and context optimization. Semantic Search & Vector Databases

Preferred candidate profile

Preferred candidate profile : AI ML Experience, Work from scratch