Artificial Intelligence Engineer

Incedo; New Delhi, Gurugram District; Hybrid; INR 700,000 - 1,100,000; Full time

Benefits offered by this job

Hybrid work model

Job summary

Incedo is seeking a Senior AI Engineer with 5–7 years of hands-on experience to design and deliver production-grade Generative AI and LLM based solutions. You will work on RAG pipelines, embeddings and vector search, leveraging LangChain and LangGraph and strong Python programming.

You will collaborate with cross-functional teams to architect scalable AI workflows, develop and expose APIs, and optimize model performance for real-time production use in a dynamic Indian context.

Qualifications

• Strong Python programming, logical reasoning and problem-solving.

Responsibilities

• Design and develop scalable Generative AI and LLM-based applications.
• Build and optimize RAG pipelines, embeddings and vector search solutions.
• Develop complex AI workflows using LangChain and LangGraph.
• Design AI agents and agentic workflows where applicable.
• Develop and integrate APIs for AI/ML applications.
• Evaluate and optimize LLM/model performance and output quality.
• Work with engineering teams on deployment, CI/CD and productionization.
• Contribute to architecture, technical design and best practices for AI solutions.
• Troubleshoot AI application issues and improve reliability and performance.

Skills

Python

LLMs

Generative AI

RAG pipelines

Prompt Engineering

Embeddings

Vector Search

LangChain

LangGraph

Model development

API development

Production AI

Supervised Learning

Unsupervised Learning

Tools

Docker

Kubernetes

AWS

Azure

Git

Jenkins

CI/CD

Microservices

Swagger

Keycloak

Elasticsearch

Kibana

Nexus

Job description

Python Dev

AI Engineer 3–7 Years

Location: Gurgaon (First Preference) / Hyderabad
Work Model: 4 Days WFO + 1 Day WFH
Joining: Immediate Joiners Preferred

Role Overview

We are looking for a Senior AI Engineer with 5–7 years of experience with strong hands-on expertise in Generative AI, LLMs, RAG, Prompt Engineering, LangChain and LangGraph. The candidate should have strong Python programming and the ability to design and implement production-ready AI solutions.

Primary Skills

• Strong Python programming, logical reasoning and problem-solving
• Strong understanding of LLMs and Generative AI
• RAG architecture and implementation
• Prompt Engineering
• Embeddings & Vector Search
• Hands-on experience with LangChain & LangGraph
• AI/ML model development, evaluation and optimization
• Supervised & Unsupervised Learning fundamentals
• API development and integration
• Experience building production-grade AI solutions

Good to Have

• Agentic AI / AI Agents
• Docker & Kubernetes
• AWS / Azure
• Git, Jenkins / CI-CD
• Microservices
• Swagger
• Keycloak
• Elasticsearch & Kibana
• Nexus / artifact management
• Model / Agent monitoring

Key Responsibilities

• Design and develop scalable Generative AI and LLM-based applications.
• Build and optimize RAG pipelines, embeddings and vector search solutions.
• Develop complex AI workflows using LangChain and LangGraph.
• Design AI agents and agentic workflows where applicable.
• Develop and integrate APIs for AI/ML applications.
• Evaluate and optimize LLM/model performance and output quality.
• Work with engineering teams on deployment, CI/CD and productionization.
• Contribute to architecture, technical design and best practices for AI solutions.
• Troubleshoot AI application issues and improve reliability and performance.