Lead AI Developer Infrastructure Security Automation

         Hiring: Lead AI Developer – Infrastructure Security Automation (L3)

Location: RCP, Navi Mumbai

Experience: 6–9 Years

Qualification: B.Tech / M.Tech

We are looking for a Lead AI Developer – Infrastructure Security Automation to architect and lead production-grade LLM, RAG, and Agentic AI solutions for security and infrastructure use cases.

 Key Responsibilities

• Architect and lead production AI/agentic systems for vulnerability triage, remediation copilots, log/incident analysis, policy-as-code review, and security data interfaces.
• Own end-to-end LLM application architecture covering model selection, prompt strategy, RAG, agents/tools, memory, evaluation, guardrails, and cost/latency optimization.
• Design production RAG systems with ingestion, chunking, embeddings, hybrid retrieval, re-ranking, evaluation, and grounding.
• Lead agentic workflows using planner/executor patterns, tool use, multi-step workflows, error recovery, and safe action boundaries.
• Build evaluation frameworks including offline benchmarks, A/B/shadow testing, human-in-the-loop review, regression testing, and continuous quality monitoring.
• Establish Responsible AI and LLM security standards including prompt-injection defense, PII handling, output validation, red teaming, audit logging, and model-risk reviews.
• Evaluate hosted and open-source models including Llama, Mistral, Qwen, with exposure to fine-tuning, distillation, and quantization.
• Lead production Python/Java backend services and internal security dashboards/frontends.
• Define engineering standards covering design/code reviews, testing, observability, metrics, evaluation dashboards, and secure-by-design practices.
• Lead AI/LLM threat modeling covering adversarial prompt attacks, model exfiltration, data poisoning, and supply-chain risks. Must-Have Skills
• Deep hands-on experience with Anthropic, OpenAI, Azure OpenAI, Vertex AI and open-source/self-hosted LLMs.
• Strong experience with LangChain, LlamaIndex, LangGraph, Haystack, or equivalent.
• Expert-level Prompt Engineering, Structured Outputs, Function/Tool Calling, Multi-step Reasoning, and Prompt-Injection Resistant Design.
• Production RAG experience with vector stores such as pgvector, Pinecone, Weaviate, Chroma, FAISS, Azure AI Search, or Vertex AI Vector Search.
• Hands-on Agentic AI experience with planner/executor patterns, state machines, tool use, observability and tracing using LangSmith, Langfuse, Arize, Helicone, or equivalent.
• Strong Python development experience; Java exposure is preferred.

 Certification – Any One Required

CISSP | CCSP | AZ-500 | AI-102 | AWS Certified Security – Specialty | Google Professional Cloud Security Engineer

 Good to Have: CISM, CEH/OSCP, Google Professional ML Engineer/AWS ML Specialty, CKA, Terraform Associate, SC-100.