Job Description

Job Summary

Fullstack python developer

Python GenAI Engineer with experience in developing AI-powered applications using Large Language Models (LLMs), RAG architectures, and Agentic AI frameworks. The role involves designing scalable AI solutions, building and optimizing retrieval pipelines, implementing vector search capabilities, and developing intelligent applications using frameworks such as LangChain and LangGraph.

Key Responsibilities

"Key Responsibilities

Design and develop scalable applications using Python

Implement and maintain AI-powered features using Large Language Models (LLMs) and agentic AI systems

Build and optimize RAG (Retrieval Augmented Generation) pipelines

Create and maintain vector databases for efficient similarity search and document retrieval

Develop and optimize embedding systems for text and data processing

Set up and manage monitoring dashboards using Grafana

Design and implement efficient data ingestion and processing pipelines

Collaborate with cross-functional teams to deliver intelligent software solutions

Participate in code reviews and contribute to technical documentation

Optimize application performance and troubleshoot production issues

Required Skills & Experience

1.

3-5 years of professional software development experience

2.

Strong proficiency in Python

3.

Advanced Python development skills, including experience with:

o

LangChain LangGraph or similar LLM frameworks

o

Hugging Face transformers

o

Vector databases (Qdrnt, Weaviate, or similar)

o

Embedding models (OpenAI, BERT, or similar)

4.

Experience implementing RAG architecture or having Knowledge on any of the below

Basic RAG Implementation:

Document chunking and preprocessing

Embedding generation and storage

Vector similarity search

LLM prompt engineering and context injection

Hybrid RAG Architectures:

Keyword-based + Dense / Sparse Vector Retrieval

BM25 + Neural Search combinations

Multi-index retrieval strategies

Hybrid re-ranking approaches

Advanced RAG Patterns:

Parent-Child Document Chunking

Recursive Retrieval

Multi-Query RAG

Hypothetical Document Embeddings (HyDE)

Query Decomposition

Self-Query RAG

RAG Pipeline Components:

Document Loaders and Parsers

Text Splitters (Recursive, Semantic, Token-based)

Embedding Models Integration

Vector Store Operations

Query Routing and Processing

Response Generation and Synthesis

RAG Enhancement Techniques:

Auto-merging Retrieved Chunks

Semantic Router Implementation

Context Window Optimization

Query Expansion Strategies

Re-ranking Mechanisms

Sentence Window Retrieval

Advanced Retrieval Methods:

Multi-Vector Retrieval

Time-Weighted Retrieval

Contextual Compression

Dynamic Few-Shot Learning

Cross-Encoder Re-ranking

5.

Knowledge of modern AI/ML concepts and applications

6.

Experience with graph databases (Neo4j, Amazon Neptune)

7.

Hands-on experience with Grafana for monitoring and visualization

8.

Strong knowledge of SQL, NoSQL ,MySqldatabases

9.

Proficiency with version control systems (Git),AWS,Data governance.Typescript/java script

Preferred Skills

Experience with:

o

AI agents and autonomous systems

o

Semantic search implementations

o

Knowledge graphs and ontologies

o

Stream processing for real-time AI applications

Containerization (Docker, Kubernetes)

Message queuing systems (Kafka, RabbitMQ)

CI/CD pipelines

Prometheus or other monitoring solutions

MLOps practices and tool"

Skill Requirements

Other Requirements