About the role

You will build and own scoped AI service features within the Cognium platform. You work within the architecture set by the Lead AI Engineer, take feature specifications and deliver production-quality implementations: a chunking strategy module, a guardrail model integration, an embedding pipeline stage, a RAGAS metric computation job. You are expected to work independently within scope — take ownership, write tests, benchmark your work, and ship to the Lead's quality bar.
You have built ML or AI features in production before. You know that a model that scores well in a notebook evaluation is not done — it needs to be packaged, served, monitored, and maintained. You are comfortable with the full lifecycle from experiment to production deployment.

What you’ll be doing

Essential Skills / Experience

Desirable Skills / Experience

• Adversarial robustness -prompt injection taxonomy (direct, indirect, multi-turn), jailbreak pattern library, red-teaming methodology, automated attack generation, bypass rate measurement and SLO definition
• Safety benchmarks -ToxiGen, HateXplain, BBQ (demographic bias), TruthfulQA (factual accuracy), PrivacyGLUE — know what they measure and what they miss for enterprise agentic use cases
• Human annotation -rubric design, inter-annotator agreement (Cohen's Kappa, Fleiss' Kappa), calibration sessions, annotation quality control, disagreement resolution

• LangChain / LlamaIndex — know their patterns even if not using them directly, understand where Cognium's custom RAG implementation diverges and why
• Pinecone / Qdrant — alternative vector database experience for comparison benchmarking and Phase 2 Weaviate migration planning
• Cohere Rerank API — commercial re-ranker benchmarking against ms-marco-MiniLM to Confirm self-hosted choice

• OpenAI Evals framework — understand its design principles for building comparable internal eval harness
• Presidio custom recogniser development — training pipeline for new entity types, rule-based recogniser authoring, regex + NLP hybrid recognition
• NVIDIA DCGM — GPU metrics collection (gpu_utilisation, memory_bandwidth, compute_utilisation), KEDA custom metric integration, MIG partition health monitoring
• Structured generation / constrained decoding — outlines, guidance, llama.cpp grammar sampling — for enforcing JSON output from vLLM without post-processing