Job Description
AI Engineer (production / apps focus):
nDesign and ship AI-powered product features (LLMs, RAG, agents, ML APIs) into our
nexisting services, working closely with backend, frontend, and data science teams.
n Integrate off-the-shelf and inhouse models (LLMs, embeddings, ML APIs) into robust
nmicroservices and user facing flows.
n Design and implement RAG and workflow/agent pipelines: retrieval, context
nassembly, tools integration, guardrails, and fallbacks.
n Own AI service reliability in production: latency, throughput, cost,
nobservability, circuitbreakers, and rollback/versioning of models and prompts.
n

n Collaborate with Data Scientists who own model training/finetuning and evaluation
ndesign; productionize their outputs as stable APIs/workflows.
n Implement logging, feedback capture, and lightweight online evaluation hooks to
nmeasure quality of AI features over time.
n Ensure safety, security, and compliance for AI features: prompt injection defenses, PII
nhandling, abuse/hallucination controls, and audit trail.




n Contribute to internal AI tooling: SDKs, templates, and reusable components to
naccelerate future AI use case.
nSkills required:
nAI Engineer role demands more than AI-based augmentation with in-depth understanding of
nconcepts like-
n-RAG
n-GenAI, LLM finetuning, Prompt engineering
n-Multi-Agent framework (langchain, langraph etc with hands on experience)
n-Eval generation and their importance
n-Tokens usage and optimisations.
n-Model/mcp gateway
nIdeal profile:
n Solid software engineering in Python (and one of Node/Java/Go),
nREST/gRPC APIs, queues, and microservices on cloud infra.
n Handson experience shipping at least one AI powered product to production (e.g.,
nsearch, recommendations, chatbots, summarization, classification)
n Practical knowledge of LLM concepts: prompts, context engineering, embeddings,
nvector search, basic evaluation metrics, and latency/cost trade-offs.
n Sol

📌 Artificial Intelligence Engineer (Gurugram)
🏢 Questhiring
📍 Gurugram