Engineering

AI Engineer

Build LLM-powered features and AI agents, including RAG, tool calling and MCP integrations, with the evaluation and guardrails a security company insists on.

Remote (India) 2–3 years Full-time

About the role

Our AI practice builds agents and LLM applications for clients and for our own AI-augmented SOC: support agents, analyst copilots, document processing and automation. As an AI Engineer you will build these systems end to end, and make sure they are measured, observable and secure against prompt injection and misuse.

What you'll do

  • Build LLM-powered features and agents using model APIs and frameworks, with tool calling and structured outputs
  • Design and implement retrieval-augmented generation (RAG) pipelines: chunking, embeddings, retrieval and re-ranking
  • Build MCP servers and tools that give agents scoped, validated access to systems
  • Create evaluation datasets and automated evals for quality, safety and cost, and run them in CI
  • Implement guardrails: input and output validation, permission-aware retrieval and human approval for risky actions
  • Instrument AI systems with tracing and monitoring, and investigate failures
  • Compare models and prompts on real tasks, balancing quality, latency and cost

What we're looking for

  • 2–3 years of software engineering experience, including at least 1 year building LLM or ML-powered features
  • Strong Python skills; TypeScript is a plus
  • Hands-on experience with LLM APIs (for example Anthropic, OpenAI or open-weight models) and prompt design
  • Experience building RAG systems with a vector store (for example pgvector, Pinecone, Qdrant or OpenSearch)
  • Understanding of LLM risks, including prompt injection, data leakage and hallucination, and how to mitigate them
  • Familiarity with evaluation practices for LLM applications
  • Comfortable with Git, testing and CI/CD

Nice to have

  • Experience with agent frameworks or the Model Context Protocol
  • Fine-tuning or serving open-weight models
  • Interest in security use cases such as alert triage or threat intelligence

How to apply

Email your CV to info@ethicalhat.com with “AI Engineer” in the subject line. A short note on the work you’re proudest of helps us a lot. We’ll get back to you after reviewing your application.

Apply for this role

Send us your details and CV for AI Engineer. We read every application and will get back to you after reviewing it.

Your details are shared only with our hiring team.