DS-Gen AI/Agnetic/LLM

Zorba AI; Maharashtra; In loco; INR 1.800.000 - 2.400.000; Tempo pieno

Descrizione del lavoro

Zorba AI is seeking a Gen AI / Agentic AI Engineer with 4+ years of Python development and hands-on experience in Generative AI, LLMs, and AI-powered applications. You will design, develop, and deploy AI solutions using modern LLMs, RAG pipelines, and autonomous agents.

You will build backend services with FastAPI or Flask, integrate vector databases, manage prompts, and optimize latency and cost while ensuring security and guardrails.

Competenze

• Hands-on experience with Generative AI and LLMs.
• Experience building RAG pipelines and vector databases.
• Experience deploying AI apps with Python backends.
• Knowledge of guardrails, data privacy, and prompt-injection mitigation.
• Familiarity with LangGraph, LangChain, CrewAI, AutoGen, or Semantic Kernel.

Mansioni

• Design and develop Generative AI apps using LLMs like GPT, Claude, or Gemini.
• Build and optimize RAG pipelines including embeddings and vector search.
• Develop autonomous AI agents and multi-agent workflows.
• Implement tool calling, function calling, and orchestration.
• Create backend services and REST APIs with Python (FastAPI/Flask).
• Integrate LLM apps with databases, APIs, and external tools.

Conoscenze

GenAI & LLMs

Agentic AI

Python

REST APIs

Cloud Platforms

Formazione

Bachelor's or Master's in CS/IT/Eng/Data Science

Strumenti

LangGraph

LangChain

CrewAI

AutoGen

Semantic Kernel

FAISS

Pinecone

Weaviate

Chroma

Azure AI Search

Docker

Kubernetes

Descrizione del lavoro

Job Description: Gen AI / Agentic AI / LLM Engineer

• Experience: 4+ Years
• Job Title: Generative AI Engineer / Agentic AI Developer
• Employment Type: Full-Time
• Job Location: As per business requirement

Job Summary

We are looking for a skilled Gen AI / Agentic AI / LLM Engineer with 4+ years of experience in Python development, Generative AI, Large Language Models (LLMs), and AI-powered application development. The ideal candidate should have hands‑on experience building LLM-based solutions, Retrieval‑Augmented Generation (RAG) pipelines, AI agents, and scalable backend services. The candidate will be responsible for designing, developing, integrating, and deploying intelligent AI applications using modern LLMs, agentic frameworks, vector databases, and cloud‑based AI services.

Key Responsibilities

• Design and develop Generative AI applications using LLMs such as GPT, Claude, Llama, or Gemini.
• Build and optimize RAG pipelines, including document ingestion, chunking, embeddings, vector search, reranking, and retrieval optimization.
• Develop autonomous and semi-autonomous AI agents using frameworks such as LangGraph, LangChain, CrewAI, AutoGen, or Semantic Kernel.
• Implement tool calling, function calling, workflow orchestration, and multi‑agent collaboration.
• Develop backend services and REST APIs using Python and frameworks such as FastAPI or Flask.
• Integrate LLM applications with enterprise systems, databases, APIs, and external tools.
• Work with vector databases such as FAISS, Pinecone, Weaviate, Chroma, or Azure AI Search.
• Implement prompt engineering, context management, conversation memory, and response optimization.
• Evaluate and improve AI application quality, including accuracy, relevance, hallucination rates, latency, and cost.
• Implement security measures, guardrails, input validation, and protection against prompt injection.
• Deploy and maintain AI applications using Docker, CI/CD pipelines, and cloud platforms.
• Collaborate with data scientists, software engineers, product teams, and business stakeholders.

Required Technical Skills

1. Generative AI & LLMs

• Hands‑on experience with Generative AI and Large Language Models.
• Knowledge of GPT, Claude, Llama, Gemini, or similar models.
• Prompt engineering, structured outputs, embeddings, and LLM API integration.

2. Agentic AI & Frameworks

• Experience with at least one framework: LangGraph, LangChain, CrewAI, AutoGen, or Semantic Kernel.
• Understanding of AI agents, tool/function calling, workflow orchestration, and agent memory.
• Ability to build tool‑using agents and multi‑step AI workflows.

3. RAG & Vector Databases

• Experience building Retrieval‑Augmented Generation (RAG) applications.
• Document processing, chunking strategies, embedding models, semantic search, and hybrid retrieval.
• Familiarity with vector databases such as FAISS, Pinecone, Chroma, Weaviate, or Azure AI Search.

4. Programming & Backend Development

• Strong Python programming skills.
• Experience with FastAPI, Flask, REST APIs, and JSON.
• Working knowledge of SQL, Git, debugging, and software development best practices.

5. Cloud & Deployment

• Exposure to AWS, Microsoft Azure, or Google Cloud.
• Familiarity with Docker, CI/CD, application deployment, and monitoring.
• Experience with Azure OpenAI, Amazon Bedrock, or Vertex AI is an advantage.

6. Evaluation & Responsible AI

• Knowledge of LLM evaluation, hallucination reduction, and response quality assessment.
• Understanding of AI guardrails, data privacy, access control, and prompt‑injection mitigation.
• Familiarity with tools such as LangSmith, RAGAS, or similar evaluation frameworks is preferred.

Good to Have

• Experience with fine‑tuning, LoRA/PEFT, or open‑source LLMs.
• Knowledge of knowledge graphs, graph‑based RAG, and advanced retrieval techniques.
• Experience with AI observability, tracing, and production monitoring.
• Familiarity with Kubernetes and scalable AI application architectures.
• Experience delivering enterprise‑grade AI assistants, copilots, or automation solutions.

Education

Bachelor's or Master's degree in Computer Science, Information Technology, Engineering, Data Science, or a related discipline.

Ideal Candidate Profile

• 4+ years of relevant software development, AI/ML, or Generative AI experience.
• Practical experience building and deploying LLM‑powered applications.
• Strong Python skills and a solid understanding of RAG and agentic AI architectures.
• Ability to develop production‑ready AI solutions and troubleshoot complex technical issues.
• Strong analytical, communication, collaboration, and problem‑solving skills.

Keywords for Candidate Sourcing

Generative AI, GenAI, Agentic AI, LLM, Large Language Models, Python, RAG, LangChain, LangGraph, CrewAI, AutoGen, Prompt Engineering, Vector Database, Embeddings, FastAPI, GPT, Azure OpenAI, Amazon Bedrock, AI Agents, Function Calling.

Skills: git,azure,kubernetes,ci/cd,docker,rest apis,python,communication,gcp,aws,sql