Job Description

About the Role

We are looking for a

Software Engineer

passionate about

Generative AI

to join our team. You will work on building intelligent, production-grade applications using cutting-edge models like GPT, LLaMA, Claude, or open-source alternatives. This is a hybrid role that combines software engineering best practices with deep interest in AI/ML, especially

LLM-based

applications such as

RAG, chatbots, agentic systems, and prompt engineering

.
You'll work alongside product managers, ML researchers, and engineers to deliver robust, scalable solutions with real-world impact.

Key Responsibilities

Build, deploy, and maintain

LLM-powered applications

using APIs or open-source models.
Implement and optimize

RAG (Retrieval-Augmented Generation)

pipelines.
Integrate and experiment with

LangChain, LlamaIndex

, and

agentic frameworks

.
Write production-grade code and deploy services in cloud environments (AWS, GCP, Azure).
Collaborate cross-functionally with design, ML, and backend teams.
Stay up to date with latest in GenAI: open models, prompting strategies, fine-tuning, etc.

Required Skills & Qualifications

2-4 years of experience in software development, preferably in Python or JavaScript/TypeScript.
Solid understanding of

data structures, algorithms, and system design

.
Experience building and deploying REST APIs or microservices.
Familiarity with

GenAI concepts

- LLMs, transformers, vector embeddings.
Hands-on experience with one or more:

LangChain / LlamaIndex

OpenAI / Cohere / Anthropic / HuggingFace models

Pinecone / Weaviate / FAISS / Qdrant (vector DBs)

Nice-to-Have (Bonus Skills)

Experience working on

chatbots

,

document Q&A

, or

agentic workflows

.
Exposure to

ML model fine-tuning

or

prompt optimization

.
Familiarity with

Docker

,

Kubernetes

, or

CI/CD pipelines

.
Contributions to open-source GenAI projects.

What You'll Get

Work on real-world, AI-first products from scratch.
Exposure to state-of-the-art LLM tools and platforms.
Learn from a collaborative, hands-on engineering + ML team.
Fast-paced environment with full ownership and impact.