AI Engineer (LLM / Chatbot / RAG)

Qentelli; Hyderabad; Presencial; INR 4 000 000 - 7 000 000; Tempo integral

Resumo da oferta

Qentelli is seeking a Lead AI Engineer to drive design, development, and deployment of conversational and generative AI systems, including LLM-powered chatbots and RAG pipelines. You will architect production-grade AI systems, mentor a team of AI/ML engineers, and collaborate with Product and Data Engineering to deliver reliable, scalable, and safe AI experiences.

You will lead development of LLM applications, design RAG components, manage prompts, implement evaluation and MLOps pipelines, and

Qualificações

• 6+ years of AI/ML engineering experience with 2+ years in a lead/senior capacity.
• Strong Python production experience for ML/AI systems.
• Hands-on experience building LLM applications (chatbots, RAG systems, generative AI).
• Practical experience with RAG components: chunking, embeddings, vector databases, retrieval & re-ranking.
• Experience with LLM orchestration frameworks: LangChain, LlamaIndex, Semantic Kernel, or similar.
• Experience with LLM APIs/platforms (OpenAI, Claude, Gemini) and hosting open-source LLMs (Llama, Mistral, Falcon).
• Familiarity with fine-tuning (LoRA, QLoRA, PEFT, RLHF) and when to apply vs prompting/RAG.
• Vector databases & semantic search (Pinecone, Weaviate, Milvus, FAISS, pgvector).
• Solid understanding of MLOps/LLMOps: versioning, monitoring, CI/CD for ML.
• Experience with cloud AI platforms (AWS SageMaker, Vertex AI, Azure OpenAI).
• Strong evaluation methods for generative AI (hallucination, relevance, latency).
• AI safety & responsible AI practices—guardrails, bias mitigation, prompt injection defense.
• Leadership in architecture decisions and roadmaps.

Responsabilidades

• Architect and lead development of LLM-based applications (chatbots, virtual assistants, copilots).
• Design and implement RAG pipelines with chunking, embeddings, vector search, re-ranking, and prompts.
• Build and maintain agentic workflows with frameworks like LangChain, LlamaIndex, or custom layers.
• Design prompt engineering and management systems, including versioning and A/B testing.
• Implement evaluation frameworks for output quality, latency, safety benchmarks.
• Build MLOps/LLMOps pipelines for deployment, monitoring, versioning, rollback (CI/CD).
• Ensure low latency, scalability, and cost-efficiency in production.
• Collaborate with Data Engineering for clean data feeds into embeddings/knowledge bases.
• Implement guardrails and safety mechanisms to mitigate prompt injection and data leakage.
• Mentor AI/ML engineers; conduct design and code reviews.
• Stay current with GenAI/LLM landscape and assess new tools/models.

Conhecimentos

Python

LLM applications

RAG pipelines

MLOps/LLMOps

Team leadership

LangChain

Vector databases

Prompt engineering

Ferramentas

LangChain

LlamaIndex

FAISS

Pinecone

Descrição da oferta de emprego

Job Summary:

We are seeking a Lead AI Engineer to drive the design, development, and deployment of our conversational AI and generative AI systems, including LLM-powered chatbots, Retrieval-Augmented Generation (RAG) pipelines, and agentic AI applications. This is a hands‑on technical leadership role you'll architect production-grade AI systems, guide a team of AI/ML engineers, and work closely with Product and Data Engineering to deliver reliable, scalable, and safe AI experiences.

Key Responsibilities:

• Architect and lead development of LLM-based applications, including chatbots, virtual assistants, and copilots.
• Design and implement RAG pipelines including chunking strategies, embedding generation, vector search, re‑ranking, and prompt construction.
• Build and maintain agentic workflows using frameworks such as LangChain, LlamaIndex, or custom orchestration layers.
• Design prompt engineering and prompt management systems, including versioning and A/B testing of prompts.
• Implement evaluation frameworks for LLM output quality hallucination detection, relevance scoring, latency, and safety benchmarks.
• Build robust MLOps/LLMOps pipelines for model deployment, monitoring, versioning, and rollback (CI/CD for AI systems).
• Ensure systems are designed for low latency, scalability, and cost‑efficiency in production environments.
• Collaborate with Data Engineering to ensure clean, structured data feeds into embeddings and knowledge bases.
• Implement guardrails, content moderation, and safety mechanisms to mitigate prompt injection, data leakage, and harmful outputs.
• Mentor and provide technical leadership to a team of AI/ML engineers; conduct design and code reviews.
• Stay current with the fast‑evolving GenAI/LLM landscape and evaluate new tools, models, and techniques for adoption.

Required Skills & Qualifications

• 6+ years of experience in AI/ML engineering, with 2+ years in a lead or senior technical capacity.
• Strong programming skills in Python, with production experience in ML/AI systems.
• Hands‑on experience building LLM applications: chatbots, RAG systems, or generative AI products in production.
• Practical experience with RAG components: chunking strategies, embedding models, vector databases, retrieval and re‑ranking.
• Experience with LLM orchestration frameworks: LangChain, LlamaIndex, Semantic Kernel, or similar.
• Experience working with LLM APIs and platforms (OpenAI, Anthropic Claude, Google Gemini) and/or hosting open‑source LLMs (Llama, Mistral, Falcon).
• Familiarity with fine‑tuning techniques (LoRA, QLoRA, PEFT, RLHF) and when to apply them vs. prompting/RAG.
• Experience with vector databases and semantic search (Pinecone, Weaviate, Milvus, FAISS, pgvector).
• Solid understanding of MLOps/LLMOps practices: model versioning, monitoring, A/B testing, CI/CD for ML.
• Experience with cloud AI platforms (AWS Bedrock/SageMaker, GCP Vertex AI, Azure OpenAI).
• Strong grasp of evaluation methodologies for generative AI (hallucination rate, groundedness, relevance, latency/cost trade‑offs).
• Understanding of AI safety and responsible AI practices — guardrails, bias mitigation, prompt injection defense.
• Experience mentoring engineers, driving architecture decisions, and leading technical roadma