Work Location: Hyderabad (Hybrid mode)

Prestige Skytech, Financial District

Experience: 5 - 8 years

Mandatory Skills: AI, ML, RAG, LLM

Key Responsibilities

- Agentic AI Development:

- Build, customize, and deploy AI agents using frameworks like LangChain, AutoGen, CrewAI, and Haystack.
- Enable agent reasoning, planning, and tool-use for complex tasks.

RAG Pipeline Design:

- Implement and optimize RAG pipelines for enterprise-scale knowledge retrieval.
- Work with vector databases (Pinecone, FAISS, Weaviate, Milvus) to manage embeddings and context injection.
- Fine-tune retrieval strategies, chunking logic, and metadata tagging for high-quality responses.

Prompt Engineering & LLM Integration:

- Develop structured prompts, context-aware query chains, and workflows for LLMs (OpenAI, Anthropic, Llama, Mistral, etc.).
- Integrate RAG-enabled LLMs into APIs, chatbots, and enterprise applications.

Automation & Platform Development:

- Create orchestration pipelines for AI agents and RAG workflows.
- Contribute to building internal AI platforms, dashboards, and monitoring systems.

Experimentation & Research:

- Stay current with new developments in RAG, multi-agent systems, and reasoning models.
- Rapidly prototype AI solutions to demonstrate value to business teams.





Required Skills

- Programming: Strong in Python; familiarity with JavaScript/TypeScript or Go is a plus.
- LLM Frameworks: Experience or coursework in LangChain, LlamaIndex, Haystack, or AutoGen.
- RAG Expertise: Understanding of RAG concepts, document indexing, embeddings, retrieval strategies, and vector DBs.
- Databases: PostgreSQL/MySQL for structured data; Pinecone, Weaviate, Milvus, FAISS for vectors.
- APIs & Cloud: Knowledge of REST/GraphQL APIs and cloud services (AWS/GCP/Azure).
- Version Control: Git, GitHub/GitLab, and CI/CD pipelines.

Preferred Skills (Good-to-Have)

- Familiarity with LangGraph and other agent orchestration libraries.
- Exposure to multi-agent collaboration patterns and reasoning models (OpenAI o1, DeepSeek-R1).
- Knowledge of document preprocessing, semantic search, and hybrid retrieval.
- Understanding of MLOps for deploying and monitoring AI pipelines.
- Experience with Docker, Kubernetes, and distributed systems.

Qualifications

- Bachelor’s degree in Computer Science, Engineering, AI/ML, or related field.
- Strong analytical skills, eagerness to experiment, and enthusiasm to learn cutting-edge AI tools.

📌 AI Engineer (Hyderabad)
🏢 Blumetra
📍 Hyderabad