Generative AI Engineer

Konstant Infosolutions Pvt. Ltd.; Jaipur; On-site; INR 900,000 - 1,900,000; Full time

Job summary

Konstantinfo in Jaipur is seeking a Generative AI Engineer to design, build, and deploy production-grade AI applications powered by large language models and multimodal systems. You will integrate foundation models with enterprise data to create scalable AI products including RAG pipelines and fine-tuned models.

You will work with Python backend (FastAPI) and tools like LangChain, LlamaIndex, LoRA/QLoRA, vector databases, and model APIs.

Qualifications

• Bachelor's or Master's degree in Computer Science, Software Engineering, AI/ML, or related technical discipline.
• 3+ years of software engineering experience, including production GenAI/LLM deployments.
• Strong proficiency in Python and backend development.

Responsibilities

• Design and build production LLM-powered applications and API integrations with major model APIs.
• Implement RAG architectures, vector DBs, and knowledge retrieval systems.
• Develop agentic AI workflows using LangChain, LlamaIndex, AutoGPT, and equivalents.
• Fine-tune foundation models using LoRA/QLoRA/PEFT methods.
• Deploy and monitor generative AI systems with guardrails, observability, and evaluation frameworks.
• Collaborate with product/data/infrastructure teams to integrate AI into workflows.

Skills

Python

Backend development

Communication

Problem solving

Team collaboration

Education

Bachelors/Masters in CS/AI/ML

Tools

FastAPI

LangChain

LlamaIndex

LoRA/QLoRA

PEFT

OpenAI API

Anthropic/Google model APIs

Job description

We’re looking for a Generative AI Engineer

LangGraph LangSmith MLflow GCP Kubernetes LoRA/QLoRA Hugging Face Google Vertex AI Anthropic API OpenAI API pgvector Weaviate Pinecone LlamaIndex LangChain FastAPI RabbitMQ Docker Azure AWS Redis Python

Job Description:

We're looking for a Generative AI Engineer to design, build, and deploy production-grade AI applications powered by large language models and multimodal generative systems. You'll integrate foundation models (GPT, Claude, Gemini, Llama) with enterprise data and workflows to create scalable, business-ready AI products including RAG pipelines, agentic systems, and fine-tuned models.

Requirements and Duties:

Design and build production LLM-powered applications and API integrations using OpenAI, Anthropic, Google, and open-source model APIsImplement RAG architectures, vector databases, and knowledge retrieval systems for enterprise AI applicationsDevelop agentic AI workflows using LangChain, LlamaIndex, AutoGPT, and equivalent frameworksFine-tune and evaluate foundation models for domain-specific enterprise use cases using LoRA/QLoRA and PEFT techniquesDeploy and monitor generative AI systems in production with appropriate guardrails, evaluation frameworks, and observabilityOptimize LLM inference performance, cost, and output quality through quantization, pruning, and distillationBuild prompt engineering and context engineering pipelines for deterministic, high-quality outputsImplement LLM observability: tracing, logging, dashboards to monitor prompts, responses, token usage, and failure casesCollaborate with product, data, and infrastructure teams to integrate AI capabilities into business workflowsStay current with emerging GenAI frameworks, multi-agent orchestration, MCP, and model routing tools

Skill and Ability:

Bachelor's or Master's degree in Computer Science, Software Engineering, AI/ML, or related technical discipline3+ years of software engineering experience, including 1–2+ years of hands-on experience building and deploying GenAI/LLM applications in production.Strong proficiency in Python and backend development (FastAPI, Flask, or Django)Hands-on experience building RAG pipelines, vector databases, and semantic search systems in productionDeep understanding of transformer architectures, LLM fundamentals, and prompt engineering techniquesExperience with fine-tuning foundation models using LoRA, QLoRA, or other PEFT methodsProficiency with GenAI frameworks: LangChain, LlamaIndex, or equivalent agent orchestration toolsKnowledge of MLOps/LLMOps practices: model deployment, monitoring, evaluation frameworks, and CI/CD for AIFamiliarity with cloud platforms (AWS, GCP, Azure) and containerization (Docker, Kubernetes)Strong problem-solving skills and ability to translate business requirements into technical AI solutionsExcellent communication skills to articulate technical decisions to both technical and non-technical stakeholdersExperience with multi-agent systems and autonomous workflow orchestrationKnowledge of model optimization techniques: quantization, distillation, pruning for inference efficiencyFamiliarity with MCP (Model Context Protocol) and emerging AI integration standardsContributions to open-source GenAI projects or published technical content on LLM developmentExperience in regulated industries with AI governance, safety guardrails, and compliance requirements

Current Openings

We consider each team member as a part of our family. Our work culture is rooted in transparency, meaningful collaboration, and inclusivity. Explore career opportunities and find the role that fits your skills.

Be a part of the most happening team around!