Gen AI Developer

Tekskills Inc.; Mumbai; On-site; INR 1,100,000 - 1,700,000; Full time

Job summary

Tekskills Inc. is hiring a Jr. Gen AI Developer (MLE Associate) with hands-on experience in building GenAI applications and agentic workflows.

The role requires strong RAG understanding, prompt engineering, and optimization techniques to deliver performant AI solutions. You will develop GenAI apps, integrate FastAPI services, and work with OpenAI/Azure OpenAI/Anthropic APIs, focusing on efficient retrieval and memory management.

Qualifications

• Strong understanding of Retrieval-Augmented Generation (RAG) with real-time implementation.
• Prompt engineering, including prompt injection risks mitigation techniques.
• Optimization techniques for GenAI workflows.
• Caching mechanisms to improve responsiveness.
• Chunking for large/multimodal data.
• Metadata filtering for efficient retrieval.
• Memory management in AI/ML workflows.

Responsibilities

• Develop and maintain GenAI applications and agentic workflows.
• Build and integrate FastAPI-based services.
• Work with LLM APIs (OpenAI, Azure OpenAI, Anthropic).
• Implement RAG pipelines with efficient retrieval strategies.
• Optimize performance using caching, chunking, and metadata filtering.
• Collaborate in coding, testing, and cloud deployments.

Skills

RAG real-time

Prompt engineering

Optimization techniques

Caching

Chunking

Metadata filtering

Memory management

SQL (engine explained)

AWS Textract (API type)

Tools

FastAPI

LangChain

LLM APIs

SQL

AWS Textract

Databricks

Job description

Job Summary

We are hiring a Jr. Gen AI Developer (MLE Associate) with hands‑on experience in building GenAI applications and agentic workflows. The candidate should have strong conceptual clarity and practical exposure to RAG, prompt engineering, and optimization techniques.

Key Responsibilities

• Develop and maintain GenAI applications and agentic workflows
• Build and integrate FastAPI-based services
• Work with LLM APIs (OpenAI, Azure OpenAI, Anthropic)
• Implement RAG pipelines with efficient retrieval strategies
• Optimize performance using caching, chunking, and metadata filtering
• Collaborate in coding, testing, and cloud deployments

Experience

3+ Years

Must-Have Skills

• Strong understanding of RAG (Retrieval-Augmented Generation) with real-time implementation
• Prompt Engineering , including Prompt injection risks Mitigation techniques
• Optimization techniques
• Caching
• Chunking for large/multimodal data
• Metadata filtering
• Knowledge of memory management in AI/ML workflows
• Hands‑on experience with SQL (must explain SQL engine used)
• Hands‑on experience with Amazon Textract (must explain API type used)

Technical Skills

• FastAPI
• LangChain
• LLM APIs (OpenAI / Azure / Anthropic)
• SQL
• AWS (Textract)
• Databricks (Good to have).