GenAI Lead / GenAI Engineer / Forward Deployed Engineer (FDE)

Vibehackers; Chennai District; On-site; INR 3,000,000 - 6,000,000; Full time

Benefits offered by this job

Job summary

Vibehackers in India is seeking an experienced Generative AI professional to design, develop, architect, and deploy enterprise-grade GenAI solutions (LLMs, RAG, Agentic AI). You will move projects from rapid prototyping to production, collaborating with customers and engineering teams to deliver scalable Python-based AI applications and establish MLOps/LLMOps and cloud architectures.

Responsibilities include building production-ready GenAI services, integrating LangChain, vector databases, and

Qualifications

• Extensive experience designing, developing and deploying GenAI solutions for enterprise use.
• Proficiency with LLMs, RAG, agentic AI, and multi-agent workflows.
• Strong Python programming and backend/frontend integration skills.

Responsibilities

• Design, build, architect, and integrate GenAI and LLM-based solutions using Python and modern AI frameworks.
• Design and implement Agentic AI solutions including agents, multi-agent workflows, orchestration, tool calling, memory and human-in-the-loop features.
• Build scalable, production-ready GenAI/AI-ML applications and services; implement microservices, APIs, and event-driven systems.
• Work with LangChain or similar frameworks, vector DBs, semantic search, knowledge graphs and GraphRAG.
• Deploy and scale AI solutions on cloud platforms (Azure, AWS, GCP) with Kubernetes, CI/CD and observability tools.
• Implement MLOps / LLMOps: model lifecycle, deployment, monitoring, governance, explainability, production readiness.
• Collaborate with product, engineering, data, and business teams; mentor engineers and define technical standards.

Skills

GenAI

LLMs

RAG

Agentic AI

Python

MLOps

LLMOps

Cloud platforms

LangChain

Vector databases

Microservices

CI/CD

REST APIs

Kubernetes

Frontend basics

Tools

Python

LangChain

REST APIs

Kubernetes

Cloud AI services

Job description

Fast prototyping and productionizing GenAI solutions with LLMs, LangChain, RAG and vector DBs — emphasizes rapid AI-driven development and deployment.

About the Role

Design, build, and deploy enterprise-grade Generative AI solutions (LLMs, RAG, agentic AI) and take them from rapid prototyping to production. Work closely with engineering teams, business stakeholders, and customers to identify use cases, implement scalable Python-based AI applications, and establish MLOps/LLMOps and cloud architectures.

Job Description

Role

Experienced Generative AI professional role to design, develop, architect, and deploy enterprise-grade GenAI solutions (LLMs, RAG, Agentic AI). Candidates will work across prototyping, production deployment, and customer-facing forward-deployed engineering engagements.

Location & Employment

• Locations: Chennai / Bangalore / Hyderabad
• Employment type: Full Time

Key Responsibilities

• Design, build, architect, and integrate Generative AI and LLM-based solutions using Python and modern AI frameworks.
• Design and implement Agentic AI solutions including agents, multi-agent workflows, orchestration, tool/function calling, MCP, memory, and human-in-the-loop capabilities.
• Build scalable, production-ready GenAI/AI-ML applications and services; implement microservices, APIs, and event-driven systems.
• Work with LangChain or similar frameworks, vector databases, semantic search, knowledge graphs, GraphRAG, and intelligent document processing.
• Design, deploy, and scale AI solutions on cloud platforms (Azure, AWS, GCP) and use cloud AI/ML services, Kubernetes, CI/CD, and observability tools.
• Implement MLOps / LLMOps: model lifecycle, deployment, monitoring, governance, explainability, and production readiness.
• Collaborate with product, engineering, data, and business teams to translate problems into scalable AI solutions; engage with customers and stakeholders; mentor engineers and define technical standards.

Required Technical Skills

• Generative AI, LLMs, Prompt Engineering, RAG, Advanced RAG
• Agentic AI, AI Agents, Multi-Agent Systems, Tool Calling / Function Calling, MCP, LLM orchestration
• Vector databases, embeddings, semantic search, reranking, Knowledge Graphs, GraphRAG
• Intelligent document processing and document ingestion pipelines
• Strong Python programming; REST APIs and backend development; full-stack AI application development
• React and/or Angular for front-end interfaces

Preferred Experience

• Experience in regulated domains (finance, banking, healthcare) or working directly with customers in consulting/forward-deployed engineering contexts
• Experience defining AI strategy, roadmaps, reference architectures, and technical standards
• Strong stakeholder management, communication, and ability to own initiatives end-to-end

Experience Levels

• Forward Deployed Engineer: 6 - 10 years
• GenAI Engineer: 6+ years
• GenAI Lead: 10+ years

Generative AI & LLMs, RAG/GraphRAG, Agentic AI, Python, Cloud AI, Vector Databases, Knowledge Graphs, MLOps/LLMOps, Data Architecture, Full-Stack Development, Solution Architecture, Customer/Stakeholder Management, Technical Leadership, Problem Solving

Skills

Generative AI & LLMs Prompt Engineering RAG Agentic AI Solution Architecture MLOps / LLMOps Cloud Architecture Full-stack Development Python Programming REST APIs Microservices Vector Databases Semantic Search Knowledge Graphs Data Architecture Model Deployment & Monitoring Stakeholder Management Technical Leadership Prototyping Customer Engagement Problem Solving