REQUIRED : LLM APIs and Agentic SDKs

- Production experience with at least one major LLM API Anthropic Claude OpenAI Azure OpenAI or Amazon Bedrock including the full surface chat completions streaming token counting context management retry backoff and rate limit handling

- Deep familiarity with tool calling function calling defining tool schemas parsing tool call results multiturn tool loops and handling partial or malformed tool outputs gracefully

- Experience with structured output constraining LLM output to a JSON schema validating it and building retry loops that reprompt on validation failure without thrashing

- Understands context window management token budgeting across a multiturn conversation what to summarise vs what to keep verbatim how context window size affects latency and cost

- Comfortable with multistep agentic loops planning tool call observe replan cycles and knows how to detect and recover from loops hallucinated tool names and stuck states

Agentic Architecture Patterns

- Designs human in the loop workflows as first class system components not as an afterthought interruption but as a structured review step with a explicit proposal format diff and approval rejection path that feeds back into the agents context

- Understands the difference between orchestrator agents and subagents knows when to delegate to a specialised subagent vs handle in one prompt and designs the handoff contract between them

- Designs stateful multisession agentic pipelines checkpoint and resume idempotent execution of steps audit trail of every agent action and human decision

- Familiar with ReAct Plan and Execute and reflection patterns knows when each applies and what their failure modes are





- Experience building provider abstraction layers wrapping LLM calls behind an interface, so the pipeline is not coupled to one vendor knows how to handle provider specific quirks token limits tool call formats refusals at the abstraction layer Retrieval Augmented Generation RAG and Ingestion

- Builds production RAG pipelines chunking strategy by section by semantic boundary by token count embedding model selection vector store indexing retrieval and reranking

- Experience ingesting heterogeneous source types of PDFs Word documents structured JSONXMLXLSX and unstructured legacy system exports each with its own extraction and preprocessing strategy

- Understands retrieval quality evaluation recallk mean reciprocal rank how to build a golden dataset and measure retrieval against it

- Experience with at least one vector store Pinecone Weaviate pgvector Chroma Qdrant including index management metadata filtering and hybrid search semantic keyword

Evaluation and AI Governance

- Builds LLM evaluation frameworks defining what correct means for a given agent task building test sets running evals as a CI gate before promoting a prompt or pipeline change

- Designs AI assurance audit trails every AI assisted action is captured what was proposed what the human approved with what version of the prompt and model query able and immutable

- Understands AI failure modes hallucination sycophancy prompt injection instruction following degradation at long context and how to defend against each in a production system

- Familiar with model evaluation dimensions factual accuracy instruction following format compliance output safety and knows which matter most for configuration authoring tasks

📌 Agentic AI Lead (Bengaluru)
🏢 Intellics Global Services
📍 Bengaluru