Senior Python Engineer (AI, ML & Agentic AI)

Saanvi Nexus; Indore District; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

Saanvi Nexus is seeking a Senior AI/ML Engineer to design, build, and deploy production-grade AI-powered applications. The role emphasizes scalable, secure, and governed LLM-based solutions with hands-on Python engineering.

You will develop AI/ML apps with Python, FastAPI, and REST microservices, implement RAG pipelines, LangChain/LlamaIndex, and train/evaluate multi-agent workflows. This is a hands-on, growth-focused senior position in Indore.

Qualifications

• 5+ years of hands-on Python development experience.
• Hands-on experience with Django/DRF/FastAPI/Flask.
• Strong knowledge of AI/ML, Generative AI, LLMs and embeddings.
• Experience with RAG pipelines and vector databases.
• Experience with LLM guardrails, governance, and security.
• Experience with cloud AI platforms and CI/CD pipelines.

Responsibilities

• Design and develop AI/ML and AI-powered applications using Python with FastAPI as the primary framework.
• Build and optimize RAG pipelines using LLMs, embeddings, and vector databases.
• Design and execute evaluation frameworks for single-agent and multi-agent systems.
• Develop GenAI solutions using LangChain, LangGraph, LlamaIndex.
• Build AI agents and multi-agent workflows for business automation.
• Implement prompt engineering, retrieval evaluation, and hallucination reduction techniques.

Skills

Python development

Django/DRF/FastAPI/Flask

AI/ML fundamentals

LLM frameworks

RAG pipelines & embeddings

Prompt engineering

Tools

LangChain

LlamaIndex

Pinecone

FAISS

Docker

Kubernetes

Job description

Role & Responsibilities

About the Role

We're looking for a Senior AI/ML Engineer to design, build, and deploy production-grade AI-powered applications. The ideal candidate has strong Python engineering fundamentals combined with hands-on expertise in AI/ML, Generative AI, LLM frameworks, RAG pipelines, and AI agent systems. This role is primarily AI/ML focused, with a strong emphasis on building scalable, secure, and well-governed LLM-based solutions.

Key Responsibilities

• Design and develop AI/ML and AI-powered applications using Python, with FastAPI as the primary framework (Django and Flask also used)
• Build and optimize RAG (Retrieval-Augmented Generation) pipelines using LLMs, embeddings, and vector databases
• Design and execute evaluation frameworks for single-agent and multi-agent systems to measure task completion, reasoning quality, tool usage, and workflow efficiency.
• Develop GenAI solutions using LangChain, LangGraph, LlamaIndex
• Build AI agents and multi-agent workflows for business process automation
• Implement prompt engineering, retrieval evaluation, and hallucination reduction techniques
• Design and enforce LLM guardrails and governance frameworks (content filtering, output validation, safety policies, compliance, and audit logging)
• Build REST APIs and microservices to integrate AI/ML components with backend systems
• Deploy AI/ML services using AWS or GCP services, Docker, Kubernetes, and CI/CD pipelines
• Work with cloud AI platforms: AWS Bedrock, GCP Vertex AI, Azure OpenAI, or OpenAI APIs
• Monitor AI/ML model performance, cost, latency, and accuracy in production environments

Required Skills

• 5+ years of strong hands-on Python development experience
• Practical experience with Django, Django REST Framework, FastAPI, or Flask
• Solid understanding of AI/ML, Generative AI, LLMs, embeddings, RAG, and semantic search
• Hands-on experience with prompt engineering, RAG evaluation, re-ranking, and hallucination handling
• Experience implementing LLM guardrails and governance frameworks (safety, compliance, monitoring, and risk controls for AI systems)
• Experience with LLM frameworks: LangChain, LangGraph, LlamaIndex
• Experience with ML/AI libraries: Pandas, NumPy, Scikit-learn, PyTorch, TensorFlow, Hugging Face Transformers
• Experience with vector databases: Pinecone, FAISS, Chroma, Weaviate, Milvus, or pgvector
• Good knowledge of AWS Bedrock (model invocation, RAG, and integration with S3, Lambda, Glue, Athena, and OpenSearch)
• Strong understanding of REST API development, microservices architecture, and API security best practices
• Hands-on experience with AWS or GCP services, Docker, Kubernetes, and CI/CD pipelines (GitHub Actions/GitLab CI)
• Experience with relational and NoSQL databases: PostgreSQL, MySQL, MongoDB, or Redis