GEN AI

Dharshanova It Solutions; India; Hybrid; INR 1,200,000 - 1,800,000; Full time

Job summary

Dharshanova It Solutions in India is seeking a skilled Generative AI Engineer to design, build, and deploy production-grade AI applications. You will bridge frontier AI models with enterprise software, collaborating with product, data, and infrastructure teams to embed intelligent features and autonomous workflows.

Responsibilities include designing scalable LLM integrations, building RAG and vector search pipelines, developing agentic frameworks, fine-tuning models, deploying pipelines with

Qualifications

• Bachelors or Masters in Computer Science, Artificial Intelligence, Machine Learning, or a related technical field.
• Experience optimizing inference latency and reducing token consumption costs at scale.
• Contributions to open-source AI repositories or published research/projects in NLP or LLMs.

Responsibilities

• Design and build scalable applications integrating LLM APIs and open-source models across multiple providers.
• Architect and optimize Retrieval-Augmented Generation (RAG) pipelines, leveraging vector databases.
• Develop multi-agent workflows and autonomous execution loops using frameworks like Lang Chain, Lang Graph, or LlamaIndex.
• Fine-tune foundation models or implement prompt engineering, in-context learning, and quantization to improve accuracy and lower latency.
• Containerize AI services via Docker and Kubernetes, deploying reliable pipelines on cloud platforms (AWS, GCP, or Azure).
• Implement robust guardrails, evaluation frameworks (e.g., Ragas, TruLens), and data privacy protocols to ensure secure and ethical AI outputs.

Skills

LLM integration

RAG architectures

Agentic frameworks

Model fine-tuning

MLOps deployment

Guardrails & safety

Education

Bachelors or Masters in CS/AI/ML

Job description

We are looking for a skilled Generative AI Engineer to design, build, and deploy production-grade AI applications.

Role & responsibilities

In this role, you will bridge the gap between frontier AI model capabilities (such as OpenAI, Anthropic, Gemini, and open-source LLMs like Llama) and real-world enterprise software. You will work cross-functionally with product, data, and infrastructure teams to embed intelligent features, RAG architectures, and autonomous agents into our core product ecosystem.

• Key Responsibilities LLM Integration: Design and build scalable applications integrating LLM APIs and open-source models across multiple providers.
• RAG & Vector Search: Architect and optimize Retrieval-Augmented Generation (RAG) pipelines, leveraging vector databases.
• Agentic Frameworks: Develop multi-agent workflows and autonomous execution loops using frameworks like Lang Chain, Lang Graph, or LlamaIndex.
• Fine-Tuning & Optimization: Fine-tune foundation models or implement prompt engineering, in-context learning, and quantization to improve accuracy and lower latency.
• Production Deployment (MLOps): Containerize AI services via Docker and Kubernetes, deploying reliable pipelines on cloud platforms (AWS, GCP, or Azure).
• Safety & Guardrails: Implement robust guardrails, evaluation frameworks (e.g., Ragas, TruLens), and data privacy protocols to ensure secure and ethical AI outputs.

Preferred Qualifications

Bachelors or Masters degree in Computer Science, Artificial Intelligence, Machine Learning, or a related technical field.

Experience optimizing inference latency and reducing token consumption costs at scale.

Contributions to open-source AI repositories or published research/projects in NLP or LLMs.