Description

Job Description

• 4–8+ years in software engineering / ML engineering; 1–3+ years in LLM/agent/RAG systems.
• Strong in Python (or TypeScript), async programming, API design, distributed systems.
• Hands-on experience with OpenAI/Azure OpenAI (Assistants API, GPT-4.1+/o-series), embeddings, structured outputs.
• Practical expertise building RAG with at least one vector DB and retrieval strategy beyond basic semantic search.
• Experience with one or more agent frameworks: LangGraph, AutoGen, CrewAI, OpenAI Assistants with tools.
• Familiarity with prompt engineering, tool/function calling, schema design, context windows, token budgets.
• Proven production deployments with monitoring, evals, and cost management.

Nice-to-Haves

• Azure ecosystem: Azure OpenAI, Azure AI Search, Azure App Service/AKS, Key Vault, Event Hubs.
• Document AI: unstructured.io, LLM-based parsers, OCR (Azure/AWS/GCP), markdown/HTML normalization.
• Knowledge graphs or retrieval re-ranking (ColBERT, SPLADE, LLM-as-judge with guardrails).
• Data privacy/security: DLP, PII redaction, RBAC, encryption-at-rest/in-transit.
• Experience with model distillation, fine-tuning, or adapters (LoRA/PEFT) for small tasks.
• Front-end integration (React, Next.js) with streaming UIs and conversation state.

Core Skills & Competencies

• LLM application design: Thinking in terms of tasks, context, tools, outputs, feedback loops.
• RAG quality: Chunking, retrieval, contextualization, citations, answerable-only logic.
• Agent orchestration: Planning, decomposition, tool-calling, memory stores, delegation policies.
• Software craft: Readable code, tests, docs, CI/CD, observability.
• Product sense: Framing AI features that deliver measurable value with safety and cost discipline.
• Communication: Clear documentation of prompts, assumptions, risks, and metrics

Key Skills

Education

Any Graduate