Position Purpose: We are looking for a highly skilled AI Infrastructure Engineer to design, deploy, and scale infrastructure powering enterprise AI and GenAI applications. The role focuses on building and optimizing vector database platforms, embedding pipelines, and scalable AI infrastructure for high-performance Retrieval-Augmented Generation (RAG) and AI agent workflows. The ideal candidate will have robust experience with Kubernetes, vector databases such as Milvus, embedding models, and distributed systems. You will work closely with AI/ML engineers, backend teams, and platform architects to ensure reliable, scalable, and production-ready AI infrastructure.
Qualification / Experience:
- B.Tech/B.E in Engineering with 5+ years of relevant experience.
Technical Skills:
- Vector Databases: Milvus deployment, schema design, and index tuning (HNSW, IVF-FLAT).
- Vector Alternatives: Experience with Qdrant, Pinecone, Weaviate, PGVector, or Chroma.
- Embeddings LLMs: Framework pipelines using OpenAI API, Hugging Face, or Cohere.
- Orchestration: Kubernetes cluster management,
Helm charts, and containerized microservices.
- Containers: Docker containerization, multi-stage builds, and registry management.
- Languages: Production-level Python development along with Go, Java, or C++.
- Storage Systems: Object storage integration including AWS S3, MinIO, or Google Cloud Storage.
Preferred Skills:
- GenAI Architectures: Experience supporting large-scale RAG applications and multi-agent platforms.
- LLM Orchestration: Hands-on familiarity with frameworks like LangChain, LlamaIndex, or custom pipelines.
- Compute Inference: Knowledge of GPU scheduling, resource optimization, and inference acceleration.
- Search Optimization: Production experience with hybrid search, metadata filtering, and index tuning.
- AI Observability: Implementation of LLM evaluation, governance, tracing, and monitoring tools.
- Familiarity with CI/CD pipelines, Infrastructure-as-Code, and cloud-native
📌 AI Infra Engineer (Mumbai)
🏢 PERSOL
📍 Mumbai