Description

Key Skills: LLM, Python, LLM Ops, Vector Database Integration, Retrieval-Augmented Generation, MLOps, Fast Api, Flask, Rest API

Roles and Responsibilities:

1. LLM Ops & Orchestration

• Operationalize LLM workloads including prompt/version management, model routing, A/B testing, guardrails, and safety enforcement.
• Design and implement agent-based workflows using frameworks such as LangChain, LangGraph, and Google Agent Development Kit.
• Establish evaluation frameworks for hallucination detection, factuality scoring, toxicity filtering, and relevance validation.
• Implement observability including prompt/response tracing, latency monitoring, cost tracking, and drift detection.

2. RAG Pipeline Engineering (Design to Production)

• Build end-to-end RAG systems: ingestion - chunking - embeddings - retrieval - reranking - generation.
• Optimize context windows, grounding strategies, and hybrid retrieval (BM25 + dense search).
• Enable multi-document and multi-tenant retrieval using metadata filtering and security-aware access control.

3. Vector Database Engineering

• Design and operate vector databases such as Pinecone, FAISS, Milvus, or Weaviate.
• Configure indexing strategies (HNSW, IVF), sharding, scaling, and lifecycle management.
• Tune recall vs latency trade-offs for optimal production performance.

4. Python & Platform Engineering

• Develop scalable microservices and APIs using Python with FastAPI or Flask.
• Design and consume REST APIs with OpenAPI/Swagger standards, pagination, rate limiting, and structured error models.
• Containerize applications using Docker and deploy on Kubernetes clusters.
• Implement CI/CD pipelines using Jenkins, GitHub Actions, or Azure DevOps.
• Integrate with AWS/Azure/GCP services for storage, queues, monitoring, and model endpoints.

5. Security, Compliance & Governance

• Implement data privacy controls including PII masking, RBAC, and audit logging.
• Apply enterprise-grade guardrails and jailbreak detection mechanisms.
• Ensure compliance with secure platform and regulatory requirements.

6. Collaboration & Documentation

• Partner with Data/ML, Product, and Security teams to deliver scalable AI solutions.
• Produce architecture diagrams, API contracts, and operational runbooks.
• Drive best practices for maintainable, observable, and secure AI platform development.

Skills Required:

• Strong expertise in LLM Ops including prompt engineering, orchestration, evaluation, and monitoring is essential.
• Practical experience building and optimizing production-grade RAG pipelines is required.
• Hands-on experience with at least one vector database platform is mandatory.
• Advanced Python engineering skills including async programming, packaging, and SOLID principles are expected.
• Experience with Docker, Kubernetes, CI/CD pipelines, and observability tooling is required.
• Familiarity with hybrid search (BM25 + dense retrieval), reranking models, and ANN configurations is advantageous.
• Exposure to model ecosystems including OpenAI, Azure OpenAI, Anthropic, Cohere, Llama, or Mistral is preferred.
• Understanding of cost optimization strategies including caching (Redis) and token usage monitoring is beneficial.

Education: Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or related field

Key Skills

Education

Any Graduate