Generative AI Engineer

Altimetrik; Pune District, Chennai, Bengaluru; Hybride; INR 900 000 - 1 500 000; Plein temps

Résumé du poste

Altimetrik in India is seeking a seasoned Generative AI Engineer to design, build, and deploy production‑level LLM and RAG solutions. You will integrate LLMs with enterprise data, orchestrate embedding pipelines, and implement robust APIs using Python.

The role emphasizes prompt engineering, evaluation, and observability, with collaboration across data engineering, cloud, product, and business teams to deliver scalable AI applications.

Qualifications

• Strong Python programming and software development fundamentals.
• Hands‑on experience with Generative AI and LLM‑based applications.
• Practical experience designing and implementing RAG architectures.
• Knowledge of embeddings, vector search, semantic retrieval, and prompt engineering.
• Experience with LangChain, LlamaIndex, or equivalent frameworks.
• Understanding of LLM evaluation, response quality, and hallucination mitigation.
• Experience integrating AI applications with APIs and enterprise data sources.

Responsabilités

• Design, develop, and deploy Generative AI applications using LLMs.
• Build and optimize RAG pipelines for enterprise use cases.
• Integrate LLMs with enterprise data sources, APIs, and knowledge bases.
• Implement document ingestion, chunking, embedding generation, semantic search, and retrieval workflows.
• Work with vector databases such as FAISS, Pinecone, Chroma, or Azure AI Search.
• Develop AI applications using frameworks such as LangChain or LlamaIndex.
• Integrate commercial or open‑source LLMs, such as OpenAI GPT models, Anthropic Claude, or Llama.
• Improve response quality through prompt engineering, retrieval tuning, evaluation, and hallucination reduction.
• Develop APIs and backend services using Python frameworks such as FastAPI.
• Implement testing, monitoring, security, and performance optimization for AI applications.
• Collaborate with data engineering, cloud, product, and business teams to deliver scalable AI solutions.

Connaissances

Python

Generative AI

LLMs

RAG architectures

Embeddings

LangChain

LlamaIndex

APIs

Prompt engineering

Outils

FAISS

Pinecone

Chroma

Weaviate

LangChain

LlamaIndex

Description du poste

Job Title: Generative AI Engineer LLM & RAG

Experience: 6–9 Years
Locations: Pune, Chennai, Bangalore

Job Overview

We are looking for an experienced Generative AI Engineer with hands‑on expertise in Large Language Models (LLMs), Retrieval‑Augmented Generation (RAG), and AI application development. The ideal candidate should have strong Python programming skills and experience building, integrating, and deploying production‑ready Generative AI solutions.

Key Responsibilities

• Design, develop, and deploy Generative AI applications using Large Language Models (LLMs).
• Build and optimize Retrieval‑Augmented Generation (RAG) pipelines for enterprise use cases.
• Integrate LLMs with enterprise data sources, APIs, and knowledge bases.
• Implement document ingestion, chunking, embedding generation, semantic search, and retrieval workflows.
• Work with vector databases such as FAISS, Pinecone, Chroma, or Azure AI Search.
• Develop AI applications using frameworks such as LangChain or LlamaIndex.
• Integrate commercial or open‑source LLMs, such as OpenAI GPT models, Anthropic Claude, or Llama.
• Improve response quality through prompt engineering, retrieval tuning, evaluation, and hallucination reduction.
• Develop APIs and backend services using Python frameworks such as FastAPI.
• Implement testing, monitoring, security, and performance optimization for AI applications.
• Collaborate with data engineering, cloud, product, and business teams to deliver scalable AI solutions.

Mandatory Skills

• Strong Python programming and software development fundamentals.
• Hands‑on experience with Generative AI and LLM‑based applications.
• Practical experience designing and implementing RAG architectures.
• Knowledge of embeddings, vector search, semantic retrieval, and prompt engineering.
• Experience with LangChain, LlamaIndex, or equivalent frameworks.
• Understanding of LLM evaluation, response quality, and hallucination mitigation.
• Experience integrating AI applications with APIs and enterprise data sources.

Good‑to‑Have Skills

• Experience with vector databases such as Pinecone, FAISS, Chroma, or Weaviate.
• Knowledge of cloud AI platforms such as AWS Bedrock, Azure OpenAI, or Google Vertex AI.
• Experience with LLM agents, tool calling, and multi‑step workflows.
• Familiarity with Docker, Kubernetes, CI/CD, and production deployment.
• Knowledge of model fine‑tuning, observability, and responsible AI practices.

Experience Requirements

• 6–9 years of overall software development or relevant engineering experience.
• Hands‑on project experience delivering LLM and RAG‑based applications.
• Strong problem‑solving, analytical, and communication skills.

Preferred Candidate Profile

Candidates should have practical experience building production‑grade Generative AI solutions, particularly RAG applications, rather than only theoretical knowledge of LLMs or prompt engineering.