Python AI Engineer (Prompt & Agentic Systems)

About the position We are seeking a hands-on Python AI Engineer with expertise in prompt engineering, agentic AI systems, and LLM-driven applications. The ideal candidate will design, develop, and productionize AI-enabled features—from retrieval-augmented generation (RAG) pipelines to autonomous multi-agent workflows—integrating with internal tools, APIs, and enterprise systems. Responsibilities • Design & Build AI Services: Develop Python-based backend services integrating LLMs for reasoning, summarization, extraction, and decision support. • Prompt Engineering: Craft, version, and optimize prompts/system instructions; implement guardrails, test variants, and improve reliability, latency, and cost-efficiency. • Agentic Systems: Architect autonomous/multi-agent workflows with planning, tool-use, memory, error recovery, and human-in-the-loop controls. • RAG Pipelines: Implement document ingestion, chunking, embeddings, vector search (semantic/re-ranking), and grounding strategies. • Evaluation & Observability: Define metrics and build evaluation suites for accuracy, factuality, and safety; establish tracing and telemetry for LLM calls. • API & Tool Integrations: Enable agents to use internal APIs, databases, and workflow engines; handle authentication, rate limits, and fallbacks. • MLOps / AIOps: Package, containerize, and deploy services (Docker/Kubernetes); manage keys, secrets, CI/CD, canary rollouts, and cost governance. • Security & Compliance: Apply data privacy principles, handle PII/redaction, enforce prompt injection defenses, and maintain audit logs. • Cross-Functional Collaboration: Partner with product, data, and security teams to translate requirements into reliable, production-ready AI features. Requirements • Strong Python skills (typing, async, testing, packaging) and experience building production APIs/services (FastAPI, Flask). • Hands-on experience with LLMs (OpenAI, Azure OpenAI, Anthropic, etc.) and embedding/RAG workflows. • Proven prompt engineering experience (few-shot strategies, tool-use instructions, output schemas, function/tool calling). • Experience with agent frameworks or custom orchestration (e.g., LangGraph, LangChain, AutoGen, or in-house equivalents). • Experience with vector databases (FAISS, Chroma, Pinecone, Weaviate) and search relevance tuning. • Familiarity with MLOps/DevOps: Docker, CI/CD, monitoring (Prometheus/Grafana), logging (OpenTelemetry), and secrets management. • Experience with testing and evaluation: unit/integration tests, offline evaluations, golden datasets, regression checks. • Practical understanding of AI safety and guardrails (prompt injection, data leakage, jailbreak prevention). Nice-to-haves • Experience with Azure/AWS/GCP AI services, key vaults, and networking. • Knowledge of Model Context Protocol (MCP) or secure tool-server patterns. • Familiarity with retrievers (BM25, hybrid search), re-rankers, or LlamaIndex/LangChain. • Experience with streaming UIs and structured outputs (JSON, Pydantic schemas). • Background in LLM fine-tuning, RLHF/DPO, or synthetic data generation. • Front-end experience for AI UX (React/Next.js, chat UI patterns). • Domain knowledge in HR/ATS, customer support, or internal enterprise workflows. Apply tot his job Apply To this Job