( /) | ()

( /) | ()

Experience: 5–10 years

Work Model: Hybrid (Currently 2 days WFO → moving to 3 days WFO)

Location: Pune

: @.

About the Role

We are looking for a hands-on GenAI Engineer who can design, build, and deploy production-grade AI solutions. This role requires strong Python expertise, experience with LLM frameworks (LangChain, LlamaIndex), and the ability to build reusable agentic components. You’ll work with both OpenAI and open-source LLMs to create scalable, cloud-ready AI applications that deliver measurable business impact.

Key Responsibilities

Design, develop, and deploy LLM-powered applications and autonomous agents for workflow automation.

Build reusable agentic components using LangChain, LlamaIndex, and in-house frameworks.

Work hands-on with Python, vector databases, embeddings, and LLM API integrations.

Integrate OpenAI (GPT family) and open-source models (Llama, Mistral, Gemini, etc.).

Prepare, clean, and transform structured & unstructured datasets for fine-tuning or model training.

Deploy scalable AI solutions on Azure (preferred) or other cloud platforms.

Implement MLOps best practices for model lifecycle management, monitoring, and optimization.

Stay current with the latest LLM, GenAI, RAG, and agentic ecosystem advancements and apply relevant innovations.

Qualifications & Skills

Required

5–10 years total experience, with 4+ years in NLP/LLMs.

Strong Python programming skills (must be hands-on).

Proven experience with:

LangChain

LlamaIndex

Agentic frameworks (custom or commercial)

Ability to design and deliver production-grade AI components, not just prototypes.

Experience with OpenAI APIs and open-source LLMs.

Strong understanding of RAG architectures, vector stores, embeddings, prompt engineering.

Cloud deployment experience — Azure preferred.

Nice to Have

Experience with Docker, Kubernetes, and scalable microservices.

Exposure to fine-tuning or model training workflows.

• Experience integrating AI into enterprise architectures.