Job Description

Location:

Remote / Hybrid / On-site (as applicable)

Experience Level: 1-3 years (relevant hands-on experience)

Employment Type: Full-time

About the Role

We are seeking an engineer with hands-on experience in building

AI agentic conversation systems

powered by modern large language models (LLMs) such as

Google Gemini, OpenAI GPT, Anthropic Claude,

or comparable platforms. The ideal candidate has a strong background in

Node.js (or equivalent JavaScript-based technologies), and is deeply familiar with AWS architecture

, services, and deployment pipelines.

In this role, you will architect, build, and iterate on intelligent conversational agents capable of reasoning, workflow orchestration, retrieval-augmented operations, tool calling, and contextual memory.

Responsibilities

Design, develop, and deploy AI-driven conversational agent systems using Gemini or other modern LLMs. Build tool-calling pipelines, RAG (retrieval-augmented generation), and agent orchestration layers. Implement and optimize real-time and asynchronous conversational flows. Integrate with external APIs, databases, vector stores, and internal services. Collaborate with product and UX to craft natural dialogue behaviors and fallback logic. Implement prompt engineering best practices, persona tuning, and system instructions. Deploy, manage, and optimize workloads on AWS leveraging services like:
o Lambda

o API Gateway

o DynamoDB

o S3

o CloudWatch

o Bedrock (optional / bonus)

o ECS or EKS (bonus)

Ensure system reliability, observability, versioning, and metrics instrumentation. Maintain security, privacy, and safety guardrails in conversational models. Continuously evaluate emerging AI frameworks, APIs, and research directions.

Required Qualifications

1+ years of hands-on experience building conversational AI systems, chatbots,or agentic workflows. Strong proficiency in Node.js (TypeScript preferred) or similar JavaScript ecosystems. Deep working knowledge of AWS cloud technologies and serverless patterns. Experience integrating with LLM APIs (Gemini, GPT, Claude, etc.). Familiarity with vector databases, embeddings, or semantic search. Understanding of prompt engineering, token management, and model constraints. Ability to write clean, modular, maintainable code and follow CI/CD practices.

Preferred / Bonus Skills

Experience with:
o Google Vertex AI

o AWS Bedrock

o LangChain / LlamaIndex

o n8n / workflow orchestration

o RAG pipelines

Exposure to UX conversational design principles. Knowledge of multi-agent orchestration frameworks. Background in NLP, reasoning engines, or AI safety guardrails.

Soft Skills

Strong communication and documentation habits. Self-driven curiosity about emerging AI capabilities. Ability to collaborate with cross-functional teams. Problem-solving mindset and experimentation culture.

What We Offer

Opportunity to build cutting-edge AI agent systems used in real products. Freedom to innovate rapidly at the frontier of LLM capabilities. Collaborative, growth-focused engineering culture. Competitive compensation and benefits.
Job Type: Full-time

Pay: ₹352,692.47 - ₹500,000.00 per year

Benefits:

Health insurance Provident Fund
Work Location: In person