Principal Engineer - AI
Safe Security11 months ago
Bengaluru, IndiaStaff+
Responsibilities
- Architect and scale LLM orchestration, RAG pipelines, vector stores, prompt pipelines, AI microservices, observability, safety, and evaluation systems.
- Build and productionize multi-turn, goal-oriented AI agents for control reviews, issue root-cause analysis, and automated responses across TPRM, CTEM, and CRQ.
- Operationalize model serving, AI APIs, model lifecycle and versioning, feature stores, embedding management, and in-memory retrieval layers with platform and DevOps teams.
- Design structured and unstructured data ingestion, semantic indexing, context retrieval, and knowledge graph integrations with Data Engineering.
- Create golden-dataset validation, LLM evaluation, safety enforcement, human-in-the-loop, monitoring, and continuous feedback frameworks.
- Mentor AI and backend engineers and translate AI goals into measurable engineering deliverables with product leaders.
Requirements
- 12+ years of total software engineering experience, including 4+ years building AI/ML systems or large-scale data/LLM infrastructure.
- Strong programming fundamentals in Python, Go, or TypeScript.
- Deep understanding of LLM architectures, prompt engineering, and RAG pipelines.
- Hands-on experience with LangChain, LlamaIndex, or equivalent orchestration frameworks.
- Experience with vector databases such as FAISS, Pinecone, Weaviate, Redis Vector, or Milvus.
- Experience with cloud model deployment using AWS SageMaker, Bedrock, Vertex AI, or custom inference APIs.
- Experience with Snowflake, Iceberg, S3, and Postgres or MySQL data systems.
- Familiarity with model versioning, ML CI/CD, real-time inference performance optimization, evaluation metrics, hallucination detection, RAG reliability, and enterprise AI safety.
- Preferred experience integrating AI into cybersecurity or risk-management products.
- Preferred familiarity with multi-agent systems and autonomous workflows, including CrewAI, LangGraph, or AutoGen.
- Preferred experience building AI evaluation dashboards and observability stacks, and knowledge of knowledge graphs, semantic search, retrieval pipelines, data governance, compliance, or SOC2/ISO 27001 environments.
- Published research, open-source contributions, or prior leadership of AI teams is a strong plus.
Benefits
- Meaningful equity for employees.
- Unlimited leave.
- Comprehensive medical insurance and wellness benefits.
- Career advancement opportunities in a rapidly growing company.
Tech Stack
Categories