Lead AI Engineer

Impetus; Dadri; On-site; INR 4,000,000 - 6,000,000; Full time

Job summary

Impetus Technologies seeks an experienced AI Engineer to design and operate scalable AI infrastructure for LLM workloads. You will build embedding pipelines, RAG architectures, and secure multi‑tenant services, collaborating with engineers, data scientists, and product teams.

You will implement production‑grade AI platforms, manage data quality and security, and optimize pipelines for performance and cost, leveraging AWS, Kubernetes, and modern tooling.

Qualifications

• 8–12 years of hands‑on software/platform engineering experience.
• Strong Python skills with async programming and API development.
• Extensive AWS experience (ECS/EKS, Lambda, API Gateway, S3, SQS, RDS).
• Data engineering expertise: ETL/ELT pipelines and vector DBs (Pinecone, Weaviate, pgvector).
• Proven production AI/LLM platform experience: embedding pipelines, RAG, API gateways, inference services.

Responsibilities

• Design and operate scalable AI platform capabilities for LLM inference and embedding pipelines.
• Develop secure, reusable APIs and microservices for AI features.
• Own platform reliability: uptime, latency, scalability and cost optimization.
• Implement secure multi-tenant infra with isolation, quota enforcement and governance.
• Build data ingestion and processing pipelines powering AI applications.

Skills

Python

AWS

ETL/ELT pipelines

Vector databases

LLM platforms

Multi-tenant design

Docker

Kubernetes

Terraform/AWS CDK

LangChain & LangGraph

Responsible AI

Education

AWS Certifications (Solutions Architect / ML Engineer)

Tools

Terraform

AWS ECS/EKS

API Gateway

Prometheus/ Grafana

Job description

Impetus Technologies is a digital engineering company focused on delivering expert services and products to help enterprises achieve their transformation goals. We solve the analytics, AI, and cloud puzzle, enabling businesses to drive unmatched innovation and growth.

Founded in 1991, we are cloud and data engineering leaders providing solutions to fortune 100 enterprises, headquartered in Los Gatos, California, with development centers in NOIDA, Indore, Gurugram, Bengaluru, Pune, and Hyderabad with over 3000 global team members. We also have offices in Canada and Australia and collaborate with a number of established companies, including American Express, Bank of America, Capital One, Toyota, United Airlines, and Verizon.

Job Summary

We are seeking an experienced AI Engineer to drive the design, development, and operation of the infrastructure, data pipelines, and platform capabilities that power our AI and LLM‑based solutions. This is a hands‑on engineering role for professionals passionate about building scalable, secure, and production‑ready AI platforms rather than developing AI models themselves.

You will collaborate with application engineers, data scientists, architects, and product teams to deliver reliable, observable, and cost‑efficient AI infrastructure that supports enterprise‑scale AI workloads.

Must‑Have Skills

• 8–12 years of hands‑on experience in software engineering and platform engineering.
• Strong proficiency in Python, including asynchronous programming, API development, and microservices architecture.
• Extensive experience with AWS, including ECS/EKS, Lambda, API Gateway, S3, SQS, and RDS.
• Strong background in data engineering, including ETL/ELT pipelines, document processing, and vector databases such as Pinecone, Weaviate, and pgvector.
• Proven experience building and operating production‑grade AI/LLM platforms, including embedding pipelines, API gateways, Retrieval‑Augmented Generation (RAG) architectures, and inference services.
• Solid understanding of multi‑tenant platform design, tenant isolation, rate limiting, quota management, and usage governance.
• Experience with containerization and orchestration technologies such as Docker, Kubernetes, and Helm.
• Hands‑on experience with observability tools including Prometheus, Grafana, OpenTelemetry, Datadog, or similar platforms.
• Experience implementing Infrastructure as Code using Terraform or AWS CDK.
• Hands‑on experience with LLM orchestration frameworks such as LangChain, LangGraph, or equivalent, with a strong understanding of agentic workflows, tool integration, and multi‑agent systems.
• Good understanding of Responsible AI practices, including AI guardrails, content moderation, toxicity detection, PII protection, and output validation.
• Experience with LLM evaluation frameworks such as RAGAS, LangSmith, or custom evaluation pipelines.
• Exposure to Voice AI, speech‑based applications, or multimodal AI systems.
• AWS Certifications such as Solutions Architect, Machine Learning Engineer, or equivalent.

Key Responsibilities

• Design, build, and manage scalable AI platform capabilities supporting LLM inference, embedding pipelines, RAG architectures, AI guardrails, and multi‑tenant AI services.
• Develop APIs and microservices that expose AI capabilities in a secure, scalable, and reusable manner.
• Own platform reliability by meeting uptime, latency, scalability, and cost‑performance objectives.
• Design and manage secure multi‑tenant infrastructure with tenant isolation, quota enforcement, usage tracking, and governance.
• Design and implement scalable data ingestion, transformation, and processing pipelines powering AI applications.
• Build and maintain vector databases, document repositories, and retrieval infrastructure to enable semantic search and RAG workloads.
• Ensure high standards of data quality, lineage, governance, and security across AI data pipelines.
• Continuously optimize pipelines for throughput, latency, scalability, and operational cost.

Technical Leadership & Collaboration

• Partner with product managers, architects, data scientists, and engineering teams to translate business requirements into scalable AI platform capabilities.
• Establish and promote platform engineering standards, architectural best practices, and reusable design patterns.
• Mentor engineers, participate in technical design reviews, and contribute to the continuous evolution of the AI platform.

For Quick Response‑ Interested Candidates can directly share their resume along with the details like Notice Period, Current CTC and Expected CTC at [e-mail]