Lead AI Engineer

Deutsche Telekom Digital Labs; Gurugram District; On-site; INR 1,800,000 - 2,800,000; Full time

Job summary

Deutsche Telekom Digital Labs in Gurugram seeks an AI Engineer to design and ship AI-powered product features, collaborating with backend, frontend, and data science teams. You will integrate LLMs, embeddings, and ML APIs into robust microservices and user flows.

You’ll own AI service reliability, latency, cost, observability, and safety/compliance, while working with data scientists to productionize models and capture feedback for continuous improvement.

Qualifications

• Experience shipping at least one AI-powered product to production.
• Strong Python software engineering, REST/gRPC, cloud microservices.
• Knowledge of prompts, embeddings, vector search, and evaluation metrics.
• Familiarity with third-party AI providers (OpenAI, Anthropic) and integration patterns.
• Hands-on with LangGraph or similar multi-agent frameworks.

Responsibilities

• Design and ship AI-powered features (LLMs, RAG, agents) into existing services.
• Integrate off-the-shelf and in-house models into robust microservices and user flows.
• Design RAG/workflow pipelines: retrieval, context, tools, guardrails, fallbacks.
• Own AI service reliability: latency, throughput, cost, observability, rollback/versioning.
• Collaborate with data scientists to productionise models as APIs/workflows.
• Implement logging, feedback capture, and lightweight evaluation hooks.
• Ensure safety, security, and compliance: prompt injection defenses, PII handling, audit trails.
• Contribute to internal AI tooling: SDKs, templates, reusable components.

Skills

Python

REST APIs

gRPC

Microservices

Cloud

LLM concepts

Latency/cost trade-offs

Agent frameworks

Tools

LangGraph

LangChain

OpenAI

Anthropic

Vector DB

Job description

Responsibilities:

• Design and ship AI-powered product features (LLMs, RAG, agents, ML APIs) into our existing services, working closely with backend, frontend, and data science teams.
• Integrate off-the-shelf and in-house models (LLMs, embeddings, ML APIs) into robust microservices and user-facing flows.
• Design and implement RAG and workflow/agent pipelines: retrieval, context assembly, tools integration, guardrails, and fallbacks.
• Own AI service reliability in production: latency, throughput, cost, observability, circuit breakers, and rollback/versioning of models and prompts.
• Collaborate with data scientists who own model training/fine-tuning and evaluation design; productionise their outputs as stable APIs/workflows.
• Implement logging, feedback capture, and lightweight online evaluation hooks to measure the quality of AI features over time.
• Ensure safety, security, and compliance for AI features: prompt injection defences, PII handling, abuse/hallucination controls, and audit trails.
• Contribute to internal AI tooling: SDKs, templates, and reusable components to accelerate future AI use cases.

Requirements:

• Strong software engineering in Python (and one of Node/Java/Go), REST/gRPC APIs, queues, and microservices on cloud infrastructure.
• Hands-on experience shipping at least one AI-powered product to production (e. g., search, recommendations, chatbots, summarisation, and classification).
• Practical knowledge of LLM concepts: prompts, context engineering, embeddings, vector search, basic evaluation metrics, and latency/cost trade-offs.
• Solid understanding of integration patterns with third-party AI providers (OpenAI, Anthropic, etc. ) and vector DB.
• Hands-on and good understanding of at least one agentic framework like LangGraph.

Skills required:

• The AI Engineer role demands more than AI-based augmentation with an in-depth understanding of concepts like RAG, GenAI, LLM finetuning, prompt engineering, multi-agent frameworks (LangChain, LangGraph, etc., with hands-on experience), eval generation and its importance, token usage and optimisations, and model/MCP gateways.