Impetus
Website:
impetus.com
Job details:
Key Responsibilities
- Design and implement scalable AI/ML and Generative AI architectures for enterprise applications.
- Develop LLM-powered applications, autonomous AI agents, and multi-agent orchestration systems.
- Architect state management and persistent memory systems for long-running AI workflows.
- Build and optimize Retrieval-Augmented Generation (RAG) pipelines using embeddings and vector databases.
- Lead the evaluation, selection, and implementation of AI technologies, frameworks, and infrastructure.
- Collaborate with stakeholders to define business requirements and convert them into technical solutions.
- Design and implement AI evaluation, observability, and monitoring frameworks.
- Develop scalable APIs, microservices, and distributed AI systems.
- Deploy and manage AI solutions on cloud platforms, primarily AWS.
- Implement MLOps/LLMOps practices for model lifecycle management and deployment automation.
- Mentor engineering teams and bridge the gap between Data Science and ML Engineering teams.
- Contribute to solution proposals, RFP responses, architecture documentation, and effort estimations.
- Ensure adherence to industry best practices, security standards, and performance engineering principles.
Required Skills & Qualifications
AI & Machine Learning
- Strong expertise in Machine Learning, Generative AI, and Large Language Models (LLMs).
- Hands-on experience designing and deploying LLM-based applications and agentic AI systems.
- Experience with multi-agent orchestration frameworks such as: LangGraph, CrewAI, AutoGen, Semantic Kernel, Strong understanding of: Prompt engineering, Embeddings, Vector databases, RAG architecture, Autonomous workflow design
- Experience implementing AI evaluation and monitoring frameworks.
- Familiarity with ML pipelines and frameworks such as MLflow, Kubeflow, or similar platforms.
- Strong programming expertise in Python. Hands-on experience with: NumPy, Pandas, Scikit-learn
- Experience designing scalable microservices and distributed systems.
- Strong API development and integration experience.
Cloud & Infrastructure
- Experience deploying AI solutions on AWS.
- Familiarity with Docker and Kubernetes.
- Understanding of AI infrastructure, vector databases, and data pipelines.
- Experience with MLOps and LLMOps platforms.
Architecture & Leadership
- Expertise in distributed systems architecture.
- Strong understanding of scalability, reliability, and performance engineering.
- Ability to design enterprise-grade AI platforms and frameworks.
- Strong technical leadership and mentoring capabilities.
- Excellent analytical, communication, and stakeholder management skills.
- Ability to explain complex AI concepts to both technical and non-technical audiences.
- Strong documentation and architecture communication skills.
Preferred Qualifications
- Years Of Experience: 14 to 18 Years
- Education/Qualification: BE / B.Tech / MCA / M.Tech
- Experience working on enterprise AI transformation initiatives.
- Exposure to autonomous AI systems and workflow orchestration platforms.
- Experience contributing to RFPs, technical proposals, and solution estimations.
- Proven track record of deploying AI solutions into production environments.
Click on Apply to know more.