AI/ML Engineer GenAI & LLM

Lookupit Solutions; Bengaluru; Hybrid; INR 1,800,000 - 3,200,000; Full time

Job summary

Lookupit Solutions in Bengaluru is seeking an AI/ML engineer to design, develop, and deploy end-to-end AI/ML and Generative AI applications. You will build LLM-based systems with RAG, vector stores, and NLP solutions including intent classification and dialogue systems.

You will deploy production pipelines, optimize latency and token usage, and collaborate with cross-functional teams to deliver AI-driven solutions on AWS and containerized infrastructure (Docker/Kubernetes).

Qualifications

• Strong Python proficiency and solid ML fundamentals.
• Experience with Generative AI, LLMs, and RAG applications.
• Familiarity with LangChain, LlamaIndex, or similar LLM frameworks.
• Knowledge of NLP/NLU, intent classification, and conversational AI.
• Experience with vector databases, embeddings and information retrieval.
• Strong AWS Cloud experience focusing on Bedrock and SageMaker.
• API development with FastAPI or similar.
• Docker, Kubernetes, and cloud deployment.
• Databases: PostgreSQL, MongoDB.
• Excellent problem solving and teamwork.

Responsibilities

• Design, develop, and deploy end-to-end AI/ML and Generative AI applications.
• Build and optimize LLM-based applications using RAG, vector databases, and hybrid retrieval techniques.
• Develop NLP solutions including intent classification, dialogue systems, text-to-SQL, and document intelligence.
• Implement AI/ML pipelines for data processing, model evaluation, inference, and performance optimization.
• Work with AWS AI services such as Bedrock, SageMaker, OpenSearch, ECS, Lambda, and S3.
• Develop scalable backend APIs and AI services using Python, FastAPI, and related technologies.
• Implement prompt engineering, context management, chunking strategies, structured outputs, and AI guardrails.
• Optimize model latency, token usage, retrieval accuracy, and overall system performance.
• Collaborate with cross-functional teams to understand business requirements and deliver AI-driven solutions.
• Deploy and maintain production-grade AI systems using Docker, Kubernetes, and cloud infrastructure.

Skills

Python

ML Concepts

Generative AI

LLMs

RAG

LangChain

LlamaIndex

NLP

NLU

Vector Databases

Embeddings

Information Retrieval

AWS Bedrock

SageMaker

APIs

FastAPI

Docker

Kubernetes

PostgreSQL

MongoDB

Tools

LangChain

LlamaIndex

FastAPI

Docker

Kubernetes

PostgreSQL

MongoDB

Job description

Key Responsibilities

• Design, develop, and deploy end-to-end AI/ML and Generative AI applications.


• Build and optimize LLM-based applications using RAG, vector databases, and hybrid retrieval techniques.


• Develop NLP solutions including intent classification, dialogue systems, text-to-SQL, and document intelligence.


• Implement AI/ML pipelines for data processing, model evaluation, inference, and performance optimization.


• Work with AWS AI services such as Amazon Bedrock, SageMaker, OpenSearch, ECS, Lambda, and S3.


• Develop scalable backend APIs and AI services using Python, FastAPI, and related technologies.


• Implement prompt engineering, context management, chunking strategies, structured outputs, and AI guardrails.


• Optimize model latency, token usage, retrieval accuracy, and overall system performance.


• Collaborate with cross-functional teams to understand business requirements and deliver AI-driven solutions.


• Deploy and maintain production-grade AI systems using Docker, Kubernetes, and cloud infrastructure.

Required Skills

• Strong proficiency in Python and Machine Learning concepts.


• Hands-on experience with Generative AI, LLMs, and RAG applications.


• Experience with LangChain, LlamaIndex, or similar LLM frameworks.


• Knowledge of NLP, NLU, intent classification, and conversational AI.


• Experience with vector databases, embeddings, and information retrieval.


• Strong understanding of AWS cloud services, particularly Bedrock and SageMaker.


• Experience in developing APIs using FastAPI or similar frameworks.


• Knowledge of Docker, Kubernetes, and cloud deployment.


• Familiarity with PostgreSQL, MongoDB, or other databases.


• Understanding of model evaluation, inference optimization, and AI system performance.

Preferred Qualifications

• Experience building production-grade AI/ML applications.


• Knowledge of time-series forecasting and anomaly detection.


• Experience with Rasa, OpenSearch, or Text-to-SQL systems.


• Familiarity with TypeScript, Node.js, or GraphQL.


• Strong problem-solving and analytical skills.


• Good communication and teamwork abilities.