Artificial Intelligence Engineer

Job Title: AI/ML Engineer

Experience: 5+ Years

Location: Remote

Job Summary

AI/ML Engineer

Key Responsibilities

LLM & RAG Systems

• Design and implement

  RAG pipelines

  using vector databases (e.g., FAISS, Pinecone, Weaviate, Chroma)
• Build

  agent-based systems

  for task orchestration, reasoning, and tool usage
• Optimize document chunking, embeddings, retrieval strategies, and re-ranking

Prompt Engineering & Intent Extraction

• Develop and maintain

  high-quality prompts

  for multi-turn conversational systems
• Implement

  intent extraction and classification

  using LLMs and traditional NLP techniques
• Continuously evaluate and improve prompt effectiveness and response accuracy

SQL Agent & Data Interaction

• Build

  SQL agents

  that translate natural language queries into optimized SQL
• Ensure correctness, performance, and safety of LLM-generated queries
• Integrate agents with relational databases (PostgreSQL, MySQL, Snowflake, etc.)

Guardrails & AI Safety

• Implement

  guardrails

  for hallucination reduction, prompt injection prevention, and data leakage control
• Apply validation layers for LLM inputs/outputs (schema checks, regex, classifiers)
• Monitor and log model behavior for compliance and risk mitigation

Engineering & Deployment

• Develop scalable APIs using

  Python (FastAPI/Flask)

  for AI services
• Collaborate with backend, data, and product teams for end-to-end delivery
• Deploy and monitor AI systems in cloud environments (AWS/GCP/Azure)
• Write clean, testable, and well-documented production code

Required Skills

Core Skills (Must-Have)

• 5+ years of experience in

  AI/ML or applied NLP

• Strong hands-on experience with

  LLMs (OpenAI, Anthropic, open-source models)

• Expertise in

  RAG architectures and agent frameworks

• Advanced

  prompt engineering

  and evaluation techniques
• Experience building

  intent extraction / classification systems

• Strong experience with

  SQL agents and database integrations

• Proven implementation of

  guardrails and AI safety mechanisms

Technical Stack

• Programming:

  Python

• LLM Frameworks: LangChain, LlamaIndex, Semantic Kernel (or similar)
• Vector DBs: FAISS, Pinecone, Weaviate, Chroma
• Databases: PostgreSQL, MySQL, Snowflake
• APIs: FastAPI / Flask
• Cloud: AWS / GCP / Azure
• MLOps/Observability: Logging, tracing, evaluation pipelines

Good to Have

• Experience with

  open-source LLMs

  (LLaMA, Mistral, Falcon)
• Knowledge of

  LLM evaluation frameworks

• Familiarity with

  CI/CD and containerization (Docker)

• Exposure to

  multi-agent systems and autonomous workflows

• Experience working in

  enterprise or customer-facing AI products