19 Nov
|
Tejas Networks
|
Bengaluru
19 Nov
Tejas Networks
Bengaluru
Role Overview
We are seeking a highly skilled AI Engineer with hands-on experience in Agentic AI, Multi-Agent Systems, LLMs, RAG, MCP, and Open-Source LLM deployment. The ideal candidate will have strong Python engineering expertise and a proven ability to design, build, optimize, and deploy production-grade AI applications.
You will be responsible for developing intelligent AI agents, optimizing LLM inference infrastructure, building domain-specific AI solutions, and creating autonomous AI systems to enhance network operations and automation.
Key Responsibilities
1. Agentic AI & Multi-Agent Systems
- Design, develop, and maintain multi-agent AI architectures using Python, LangGraph, LangChain, and custom orchestration frameworks.
- Implement hierarchical agent orchestration, intelligent task delegation, energetic routing, tool-calling mechanisms, and autonomous workflows.
- Build state-machine-driven agent workflows with persistent memory and contextual reasoning.
- Develop and maintain applications leveraging the Model Context Protocol (MCP).
- Design scalable agent state management, memory management, and long-context handling systems.
2. LLM Engineering & LLMOps
- Deploy, serve, and optimize open-source LLMs using vLLM and related inference frameworks.
- Improve inference throughput, latency, GPU utilization, memory efficiency,
and overall serving performance.
- Implement caching, load balancing, rate limiting, request routing, and fault tolerance strategies.
- Monitor AI applications using Langfuse and other observability platforms.
- Build automated evaluation pipelines to assess response quality, reliability, accuracy, and performance.
- Establish production-grade LLMOps practices, CI/CD pipelines, and model monitoring workflows.
3. Retrieval-Augmented Generation (RAG)
- Design and implement enterprise-grade RAG systems for structured and unstructured data.
- Develop document ingestion pipelines including OCR, preprocessing, semantic chunking, embedding generation, and indexing.
- Integrate vector databases and hybrid retrieval mechanisms.
- Implement custom retrievers, reranking pipelines, and retrieval optimization strategies.
- Improve retrieval accuracy, relevance, scalability, and response grounding.
4. Backend & Platform Engineering
- Develop scalable backend services using FastAPI and REST APIs.
- Work with PostgreSQL, ClickHouse, Redis, and other data platforms.
- Build containerized AI applications using Docker.
- Collaborate closely with platform, infrastructure, and domain teams to deliver production-ready AI solutions.
📌 Senior Engineer- AI (Bengaluru)
🏢 Tejas Networks
📍 Bengaluru