Senior Artificial Intelligence Engineer

SNP Cloud Technologies; Hyderabad; On-site; INR 2,000,000 - 4,000,000; Full time

Job summary

SNP Cloud Technologies is seeking a hands-on Senior AI Engineer to design, build, and ship production-grade AI features using Python, FastAPI/Flask, and modern AI frameworks. You will implement RAG pipelines, LLM-powered services, and agentic workflows, collaborating with the AI & ML team and cross-functional partners.

The role emphasizes clean code, end-to-end ownership, and growth toward technical leadership within Azure OpenAI and related toolchains.

Qualifications

• Bachelor’s or Master’s in Computer Science, AI, Data Science or related field or equivalent experience.
• 3–5 years of professional software engineering with 1.5–2 years in AI/ML or Generative AI projects.

Responsibilities

• Design, build, and ship production-grade AI features (RAG pipelines, LLM-powered services, ML models).
• Own features end-to-end from design to deployment; work with Technical Lead and cross-functional teams.
• Mentor junior engineers, participate in code reviews, and write technical documentation.

Skills

Python

FastAPI/Flask

REST API development

LLM development

Prompt engineering

Vector databases

Data handling (Pandas, NumPy)

ML frameworks (Scikit-learn, PyTorch,/

Git & CI/CD

Team collaboration

Education

Bachelor’s or Master’s degree in Computer Science / AI / Data Science or related field

Tools

LangChain

LangGraph

LlamaIndex

Semantic Kernel

Azure OpenAI

Azure ML

Docker

MLflow

Kubeflow

Azure ML pipelines

Job description

Job Description :

Senior AI Engineer Python & Generative AI

• Job Title: Senior AI Engineer
• Department: AI & ML
• Experience: 35 years
• Location: SNP Cloud Technologies, 12th Floor, Western Aqua, Cross Street 1, Whitefields, HITEC City, Hyderabad, Telangana 500081
• Job Type: Full-time, Regular, Work from Office
• Reports To: Technical Lead, AI

Summary

We are looking for a hands‑on Senior AI Engineer with strong Python skills and practical experience building AI and Generative AI applications. You will design, build, and ship production‑grade AI features — from RAG pipelines and LLM‑powered services to ML models and agentic workflows — working closely with the Technical Lead and cross‑functional teams. This is a core individual‑contributor role for an engineer who writes clean code, owns features end to end, and wants to grow toward technical leadership

.

Responsibilities

Python & Backend Engineering:

• Design, develop, and maintain Python services, REST APIs, and microservices (FastAPI / Flask) that expose AI capabilities.
• Write clean, modular, well‑tested code following Python best practices (typing, linting, unit/integration tests).
• Build data processing and ingestion pipelines (document parsing, chunking, embedding, ETL) that feed AI/ML workloads.
• Containerise services with Docker and contribute to CI/CD pipelines for automated testing and deployment.
• Debug, profile, and optimise services for latency, reliability, and cost.

Generative AI & LLM Applications:

• Build RAG (Retrieval‑Augmented Generation) pipelines end to end — ingestion, chunking strategy, embeddings, vector search, re‑ranking, and grounded response generation.
• Develop LLM‑powered applications using Azure OpenAI and other model providers, with effective prompt engineering and structured outputs.
• Implement agentic workflows — tool/function calling, planning agents, and multi‑agent orchestration — using frameworks such as LangChain, LangGraph, Semantic Kernel, or AutoGen.
• Build or integrate MCP (Model Context Protocol) servers and tools to connect agents with enterprise systems and data.
• Work with vector databases (Azure AI Search, Pinecone, Qdrant, Chroma, FAISS, pgvector, etc.).
• Set up evaluation for LLM outputs (relevance, groundedness, hallucination checks) and apply guardrails, content safety, and PII handling.

Machine Learning & Azure AI:

• Use Azure AI services (Azure OpenAI, AI Search, Document Intelligence, Vision, Language, Speech, Azure ML) to build intelligent applications.
• Train, fine‑tune, and evaluate ML/DL models using Scikit‑learn, PyTorch, or TensorFlow where the use case requires it.
• Track experiments and manage models with MLflow or Azure ML; support model deployment and monitoring in production.

Collaboration & Ownership:

• Take ownership of features from requirement to production, including design, estimation, development, testing, and deployment.
• Work with the Technical Lead, product, and business teams to turn requirements into technical solutions.
• Take part in code reviews and mentor junior engineers on coding standards and AI engineering practices.
• Write clear technical documentation and present solutions or POCs to stakeholders.
• Keep up with advances in LLMs, agent frameworks, and MLOps, and propose improvements to the current stack.

Qualifications:

Required:

• Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or a related field (or equivalent experience).
• 3–5 years of professional software engineering experience, with at least 1.5–2 years hands‑on in AI/ML or Generative AI projects.

Strong expertise in:

• Python (FastAPI / Flask, asyncio, OOP, Pydantic) and REST API development.
• LLM application development — prompt engineering, function/tool calling, and RAG pipelines.
• At least one LLM/agent framework (LangChain, LangGraph, LlamaIndex, Semantic Kernel, or similar).
• Vector databases and embedding models.
• Data handling with Pandas and NumPy.
• Hands‑on experience with at least one ML framework (Scikit‑learn, PyTorch, or TensorFlow).
• Git, Docker, and working within Agile and CI/CD processes.
• Good communication and problem‑solving skills, with the ability to explain technical decisions clearly.

Preferred:

• Experience with Microsoft Azure — Azure OpenAI, Azure AI Search, Azure ML, Azure Functions / App Service / AKS.
• At least one GenAI or ML solution deployed to production (not just POCs).
• Exposure to agentic architectures — tool-using agents, planning agents, or multi‑agent workflows.
• Familiarity with MCP (Model Context Protocol) — building MCP servers, exposing tools, or integrating agents with MCP.
• Experience with LLM evaluation and observability tools (RAGAS, DeepEval, Langfuse, LangSmith, Azure AI Foundry evaluations).
• Knowledge of MLOps tools such as MLflow, Kubeflow, or Azure ML pipelines.
• Exposure to fine‑tuning techniques (LoRA / PEFT) or open‑source LLMs (Llama, Mistral, etc.).
• Relevant certifications (e.g., Microsoft Azure AI Engineer Associate – AI-102).