AI Engineer – Multi-Agent Systems & NLP / ML
Location : Gurugram, India (On-site, Full-time)
Experience : 2–4 years
About LeapX
LeapX is building the next generation of AI-powered advertising platforms. Our products are redefining how brands run campaigns with speed, precision, and intelligence.
We’re looking for an AI Engineer (Multi-Agent Systems & NLP / ML) to design, train, and productionize intelligent multi-agent workflows that form the backbone of our platform. This role is ideal for someone who thrives at the intersection of machine learning, NLP, and systems engineering .
What You’ll Do
Design & Build Multi-Agent Workflows : Architect agentic environments (e.g., LangGraph or similar frameworks) with robust orchestration, memory, retries, and guardrails.
Develop ML / NLP Models : Train, fine-tune, and deploy PyTorch-based models for NLP tasks such as intent detection, summarization, embeddings, and structured reasoning.
Integrate Agents with ML Pipelines : Connect model outputs with decision-making agents, ensuring smooth handoffs between reasoning, planning, and execution steps.
Infrastructure & Deployment : Scale AI services on AWS (ECS / EKS / Lambda, S3, CloudWatch) using Docker and CI / CD workflows.
Observability & Evaluation : Set up eval harnesses, logging, tracing, and performance monitoring (Langfuse, Phoenix, or equivalent).
Cross-team Collaboration : Work closely with backend, product, and AI research teams to integrate multi-agent workflows into customer-facing products.
Innovation & Research : Stay ahead of emerging multi-agent frameworks, ML architectures, and optimization techniques to bring cutting-edge capabilities into production.
What We’re Looking For
Core Skills :
2–4 years in AI / ML engineering with strong Python and PyTorch expertise.
Solid experience in NLP (transformers, embeddings, fine-tuning, sequence modeling).
Hands-on exposure to agent frameworks (LangGraph, Haystack Agents, AutoGen, or equivalent).
Systems Knowledge :
Understanding of multi-agentic environments, state management, and inter-agent communication.
Familiarity with RAG pipelines and vector databases (Postgres / pgvector, Pinecone, Weaviate, etc.).
Deployment & Ops :
Proven ability to deploy and scale ML services in production using cloud infrastructure (AWS preferred).
Mindset :
Strong problem-solving skills with ability to move from prototype → production.
Curiosity to explore new approaches in agent orchestration and ML research.
Bonus :
Experience with ad-tech APIs (Google Ads, Meta).
Knowledge of LoRA / QLoRA fine-tuning or GPU inference frameworks (vLLM, TGI).
Contributions to open-source agent frameworks or ML libraries.
What We Offer
Opportunity to shape the multi-agent intelligence stack that powers LeapX products.
A fast-moving, high-ownership environment where your work directly impacts global brands.
Close collaboration with experienced founders and technologists.
Competitive Salary + ESOP + potential to lead the AI agents / ML charter in the future.
Work from our Gurugram office with a culture of speed, creativity, and excellence .
If you are interested in this role, please fill this below form. It will take 15 / 20 mins, hence kindly be prepapred accordingly.
do note, if you just apply using Easy Apply button, we wont be able to move ahead with your candidature.
Ml Engineer • Faridabad, India