Artificial Intelligence Engineer

Expleo; Mumbai; Presencial; INR 2.000.000 - 4.000.000; Jornada completa

Descripción de la vacante

Expleo Group in Mumbai is seeking an experienced AI Engineer to drive Generative AI initiatives, build LLM-based applications, and design agent-based workflows. You will work with Python, REST APIs, and modern AI tooling to deliver production-grade AI solutions.

The role emphasizes hands-on development with AI agents, RAG, and deployment pipelines, collaborating across teams to scale AI capabilities in enterprise environments.

Formación

• Expertness in Generative AI and LLMs.
• Proven ability to build AI agents or agentic AI systems.
• Strong knowledge of RAG architecture and embeddings.

Responsabilidades

• Generative AI & LLMs development and strategy.
• Build AI agents and orchestrate workflows.
• Design and implement AI applications with Python and REST APIs.

Conocimientos

Generative AI

LLMs

AI Agents

Python

REST APIs

Microservices

Asynchronous programming

Prompt engineering

Tool calling

AI deployment

Herramientas

LangGraph

LangChain

AutoGen

CrewAI

Pinecone

Weaviate

Milvus

Chroma

pgvector

Descripción del empleo

Role & responsibilities

• Generative AI & LLMs
• Strong hands-on experience with Generative AI and Large Language Models (LLMs).
• Proven experience building AI Agents / Agentic AI systems.
• Strong understanding of RAG architecture.
• Experience with prompt engineering, function/tool calling, structured outputs, and guardrails.
• Experience with models such as OpenAI, Azure OpenAI, Anthropic, Gemini, Llama, or equivalent.
• Understanding of context management, token optimization, model selection, and LLM application architecture.
• Agent Frameworks & Orchestration
• Hands-on experience with one or more frameworks such as LangGraph, LangChain, AutoGen, CrewAI, or equivalent.
• Experience designing single-agent and multi-agent workflows.
• Understanding of agent orchestration, state management, memory, tool execution, and human-in-the loop workflows.
• Python & AI Application Development
• Strong hands-on experience with Python.
• Experience developing production-grade AI applications and services.
• Experience building REST APIs and microservices for AI applications.Strong understanding of asynchronous programming and event-driven application patterns is preferred.
• RAG & Enterprise Data
• Experience with vector databases such as Pinecone, Weaviate, Milvus, Chroma, pgvector, or equivalent.
• Strong understanding of embeddings, chunking, retrieval, reranking, and semantic search.
• Experience working with structured, semi-structured, and unstructured enterprise data.
• Strong understanding of knowledge bases and enterprise search.
• AI Engineering & Deployment
• Experience deploying AI applications using Docker and Kubernetes.
• Experience with AWS, Azure, or GCP.
• Understanding of CI/CD and AI application deployment pipelines.
• Experience with LLM evaluation, observability, tracing, and monitoring.
• Familiarity with LangSmith, MLflow, or equivalent AI observability/evaluation tools is preferred

Preferred candidate profile

• 4 to 8 years of relevant experience in AI, Generative AI, NLP, or related areas.
• Strong hands-on experience building and deploying production-grade Generative AI solutions.
• Proven experience building LLM-based applications and AI Agents.
• Strong problem-solving, system-design, and communication skills.