About the role :

You will build and own scoped AI service features within the Mind.AI 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.

Role & responsibilities :

RAG & Knowledge Retrieval :

- Build and optimise enterprise-grade RAG pipelines for accurate knowledge retrieval

- Develop document ingestion, indexing, embedding, and retrieval workflows

- Implement hybrid search, re-ranking, and citation-based response generation

- Improve retrieval quality, relevance, and scalability across large knowledge bases

AI Safety & Guardrails :

- Implement PII detection, data protection, and content redaction controls

- Integrate prompt injection, toxicity, and misuse detection mechanisms

- Build AI guardrails to ensure safe, compliant, and trustworthy responses

- Develop automated response quality and faithfulness evaluation frameworks

Memory & Knowledge Management :

- Design and implement long-term AI memory frameworks

- Build user, agent, and organisational knowledge retention capabilities

- Develop knowledge graph and graph-based retrieval solutions

- Optimise context management through intelligent summarisation and memory retrieval

Evaluation & Optimisation :

- Define and implement AI evaluation metrics and testing frameworks

- Create and maintain golden datasets for model validation

- Conduct experiments to improve retrieval, reasoning, and response quality

- Drive continuous performance optimisation through benchmarking and analytics

Platform Engineering :

- Design scalable, production-ready AI services and APIs

- Optimise latency, throughput, reliability, and cost of AI workloads

- Build monitoring, observability, and auditability for AI systems

- Collaborate with platform, data, and product teams to deliver enterprise AI solutions

Agentic AI & Multi-Agent Systems :

- Design and develop autonomous AI agents and multi-agent workflows

- Build orchestration frameworks for planning, reasoning, and task execution

- Implement agent memory, tool calling, and decision-making capabilities

- Enable enterprise-scale deployment, governance, and monitoring of agentic solutions

Skills and Experience Required :

Systems Architecture :

- Experience with distributed systems and microservices architecture.

- Knowledge of event-driven systems using Kafka and NATS.

- Skilled in REST APIs, real-time communication, API security, JWT, rate limiting, and resilience patterns.

LLM Orchestration & Agentic AI :

- Experience building AI agents using LangChain and LangGraph.

- Skilled in single-agent and multi-agent workflows, including ReAct, Planning, and Tool-Use patterns.

- Strong understanding of prompt engineering, context management, memory, and multi-LLM integration.

Python & AI/ML Stack :

- Strong programming skills in Python, FastAPI, and Pydantic.

- Experience with NLP and AI frameworks including SpaCy, Sentence Transformers, PyTorch, and Hugging Face.

- Knowledge of ONNX, LoRA/QLoRA fine-tuning, vLLM, LangChain, LangGraph, and RAGAS.

Retrieval & Search :

- Experience designing Retrieval-Augmented Generation (RAG) solutions.

- Skilled in document chunking, embeddings, vector databases, and Elasticsearch (BM25).

- Knowledge of hybrid search and cross-encoder re-ranking techniques.

Evaluation, Safety & Responsible AI :

- Experience with AI evaluation frameworks such as RAGAS and DeepEval.

- Skilled in benchmarking, LLM-as-a-Judge, and human-in-the-loop evaluation.

- Knowledge of AI safety, prompt injection prevention, red teaming, and industry safety benchmarks.

Data Platforms :

- Experience with PostgreSQL, pgvector, and Redis.

- Knowledge of Kafka for event streaming and data processing.

- Skilled in building and working with Neo4j knowledge graphs.