Analytics_Senior Associate Data Scientist with Python

NITYO; Bengaluru; On-site; INR 1,200,000 - 1,800,000; Part time

Job summary

NITYO is seeking a Senior Associate Data Scientist with Python expertise to architect and deliver LLM-based solutions across India. The role focuses on RAG, retrieval pipelines, and compliant AI, with exposure to LangChain/LlamaIndex and multiple vector databases. You will collaborate with product teams and mentor junior engineers.

Contract position with locations in Bengaluru, Chennai, Hyderabad, Pune, and Trivandrum. Remote details are not specified.

Qualifications

• 4+ years of Python experience (Core Python, OOP, data structures)
• Experience with LLMs, RAG, LangChain/LlamaIndex, and Vector DBs (Pinecone/Milvus/FAISS/Weaviate/pgvector)
• Proficiency with Azure OpenAI, AWS Bedrock, Vertex AI; Prompt Engineering and LLMOps (CI/CD, monitoring)
• Familiarity with Kubernetes/Docker, API integration, RAI/PII guardrails, and retrieval evaluation (nDCG, recall@k)
• Desirable: search & ranking (BM25), multimodal AI, SharePoint/Confluence connectors, Kafka, LoRA/QLoRA, quantization, cost optimization, banking domain familiarity
• Relevant experience: 4-9 years
• Educational qualification: Degree

Responsibilities

• Architect and build LLM-based solutions such as RAG, agents, copilots, document Q&A, and summarization
• Design retrieval pipelines using vector/hybrid search, chunking, embeddings, and metadata
• Implement LLM orchestration with LangChain/LlamaIndex and API integrations
• Build guardrails for safety, PII redaction, and jailbreak prevention
• Manage vector databases and document ingestion pipelines
• Set up evaluation frameworks for groundedness, hallucination, and task metrics
• Ensure Responsible AI, data privacy and compliance
• Build LLMOps pipelines, including CI/CD, versioning, monitoring, and cost optimization
• Optimize model performance for latency, throughput, reranking
• Collaborate with Product, SMEs, and Compliance; mentor junior engineers

Skills

Python

LLMs

LangChain/LlamaIndex

Vector DBs

APIs

Guardrails

PII/Privacy

Performance

Azure OpenAI

Kubernetes

Education

Degree

Tools

Pinecone

Milvus

FAISS

Weaviate

pgvector

LangChain

LlamaIndex

Job description

Senior Associate Data Scientist with Python

We are seeking a highly skilled Senior Associate Data Scientist with expertise in Python to join our team on a contract basis. This role involves architecting and building advanced LLM-based solutions, designing retrieval pipelines, and ensuring compliance with Responsible AI standards. The position is available in multiple locations across India, including Bengaluru, Chennai, Hyderabad, Pune, and Trivandrum.

Key Responsibilities

• Architect and build LLM-based solutions such as RAG, agents, copilots, document Q&A, and summarization.
• Design retrieval pipelines using vector/hybrid search, chunking, embeddings, and metadata.
• Implement LLM orchestration with LangChain/LlamaIndex and integrate with enterprise systems via APIs.
• Build guardrails for safety, PII redaction, and jailbreak prevention.
• Manage vector databases like Pinecone, Milvus, FAISS, Weaviate, and pgvector, along with document ingestion pipelines.
• Set up evaluation frameworks for groundedness, hallucination rate, task metrics, nDCG, and recall@k.
• Ensure Responsible AI, compliance, and data privacy (PII/PCI/GLBA).
• Build LLMOps pipelines, including CI/CD, versioning, monitoring, and cost optimization.
• Optimize model performance for latency, throughput, reranking, and caching.
• Collaborate with Product, SMEs, and Compliance teams; mentor junior engineers.

Requirements

• Minimum 4 years of experience in Python, Core Python, OOP concepts, data structures, lists, dictionaries, and Python scripting.
• Experience with LLMs, RAG, LangChain/LlamaIndex, and Vector DBs (Pinecone/Milvus/FAISS/Weaviate/pgvector).
• Proficiency in Azure OpenAI, AWS Bedrock, Vertex AI, Prompt Engineering, and LLMOps (CI/CD, monitoring, versioning).
• Familiarity with Kubernetes/Docker, API integration, RAI/PII guardrails, and retrieval evaluation (nDCG, recall@k).
• Desired skills include search & ranking (BM25, hybrid search), multimodal AI, ASR/NLP, SharePoint/Confluence connectors, Kafka streaming, LoRA/QLoRA, quantization, cost optimization, and banking domain familiarity.
• Relevant experience of 4-9 years.
• Educational qualification: Degree.

Work Arrangements

• Contract position with locations in Bengaluru, Chennai, Hyderabad, Pune, and Trivandrum.
• Remote work details are not specified.