AI Engineer

Umanist NA; Maharashtra; Hybrid; INR 1,800,000 - 2,800,000; Full time

Job summary

Umanist NA in Pune, Maharashtra, is seeking an experienced AI Engineer to design, develop and scale production-grade AI and Generative AI applications. The role involves building LLM-powered applications, RAG pipelines, agentic systems, automation workflows, APIs, and enterprise integrations.

Hybrid work model; 4-8 years of software/AI experience preferred. You will work with Python/TypeScript, distributed systems, Kubernetes, Docker, and cloud platforms across AWS/Azure/GCP while collaborating

Qualifications

• 4-8 years of software engineering and/or AI experience.
• Strong Python or TypeScript proficiency.
• Hands-on experience with LLMs and GenAI.
• Experience building RAG pipelines and AI APIs.
• Familiarity with cloud platforms (AWS/Azure/GCP) and DevOps practices.

Responsibilities

• Design, develop, and deploy end-to-end AI and GenAI applications.
• Build LLM-powered apps, RAG pipelines, AI agents, and automation workflows.
• Develop scalable APIs and_microservices for AI solutions.
• Design data pipelines and retrieval systems.
• Work on prompt engineering, model evaluation, and performance optimization.
• Build reliable and scalable AI services suitable for production environments.
• Implement observability, monitoring, and reliability practices for AI applications.
• Collaborate with stakeholders to develop AI-driven solutions.
• Mentor junior engineers and support knowledge-sharing initiatives.

Skills

Python

TypeScript

LLMs

RAG pipelines

APIs & Microservices

Kubernetes

Docker

CI/CD

AWS

Azure

GCP

Distributed systems

Communication skills

Tools

Kubernetes

Docker

CI/CD tooling

Job description

Location: Pune, Maharashtra

Work Mode: Hybrid

Experience: 4-8 Years

Notice Period: Immediate to 45 Days(525)

Role Summary

We are looking for an experienced AI Engineer to design, develop, and scale production-grade AI and Generative AI applications.

The role involves building LLM-powered applications, RAG pipelines, agentic systems, automation workflows, APIs, and enterprise integrations. The ideal candidate should have strong software engineering fundamentals, hands‑on AI/GenAI experience, and excellent communication skills.

Key Responsibilities

• Design, develop, and deploy end-to-end AI and GenAI applications.


• Build and integrate LLM-powered applications, RAG pipelines, AI agents, and automation workflows.


• Develop scalable APIs and microservices for AI solutions.


• Design and implement robust data pipelines and retrieval systems.


• Work on prompt engineering, model evaluation, and performance optimization.


• Build reliable and scalable AI services suitable for production environments.


• Implement observability, monitoring, and reliability practices for AI applications.


• Work with distributed systems and cloud-based architectures.


• Collaborate with technical and business stakeholders to develop AI-driven solutions.


• Contribute to system design, engineering best practices, and technical documentation.


• Mentor junior engineers and support knowledge-sharing initiatives.

Must-Have Skills

• 4-8 years of experience in software engineering and/or AI roles.


• Strong hands‑on programming experience in Python or TypeScript.


• Practical experience working with Large Language Models (LLMs).


• Hands‑on experience building RAG pipelines.


• Experience with AI/ML frameworks and libraries.


• Strong understanding of Artificial Intelligence and Machine Learning concepts.


• Experience building and integrating APIs and microservices.


• Experience working with distributed systems.


• Familiarity with Kubernetes and Docker.


• Experience with CI/CD pipelines and DevOps practices.


• Hands‑on experience with at least one cloud platform: AWS, Azure, or GCP.


• Excellent verbal and written communication skills.


• Strong problem-solving and collaboration skills.

Nice-to-Have Skills

• Experience with agentic AI and agent frameworks such as:
  
  
  
  • LangGraph
  
  
  • Semantic Kernel
  
  
  
  


• Knowledge of vector databases.


• Understanding of hybrid search and advanced retrieval techniques.


• Strong knowledge of system design, scalability, and performance tuning.


• Experience with enterprise system integrations, such as:
  
  
  
  • CRM
  
  
  • ERP
  
  
  • ITSM
  
  
  
  


• Experience designing production-grade AI platforms and services.


• Knowledge of AI application observability, evaluation, and monitoring.

Candidate Requirements

• Candidates should have minimum 2 years of stability in an organization.


• Immediate to 45 days notice period preferred.


• Local Pune candidates are preferred.


• Temporary accommodation may be provided for a couple of weeks.


• Excellent communication skills are essential as this is a client‑facing role involving regular interaction with stakeholders and teams.

Interview Process

2 Technical Rounds → 1 Client Round → HR Round

Keywords

AI Engineer | Generative AI | GenAI | LLM | Large Language Models | RAG | AI Agents | Python | TypeScript | Machine Learning | APIs | Microservices | Kubernetes | Docker | CI/CD | AWS | Azure | GCP | Vector Database | Hybrid Search

Skills: advanced retrieval techniques,kubernetes,ai/ml frameworks,vector databases,hybrid search,apis,distributed systems,ai roles,azure,typescript,rag pipelines,aws,artificial intelligence strategy,software engineering,python,microservices,llms,ci/cd pipelines,agentic ai,docker,devops