Back to Jobs

Agentic AI

Actively Reviewing the Applications

Blueberry Semiconductors

India, Karnataka Full-Time On-site

Posted 6 hours ago • Apply by June 9, 2026

Job Description

Key Responsibilities

Agentic AI & MLOps Engineering

Design, build, and deploy agentic AI systems using LLMs, tool orchestration, and multi-agent workflows. Experience building multi-agent systems or autonomous workflows.
Develop and optimize RAG pipelines using vector databases and retrieval strategies.
Build robust prompt frameworks, evaluation pipelines, and guardrails for safe and reliable AI behaviour.
Integrate LLM-based systems with enterprise APIs, data platforms, and operational systems.
Implement observability, feedback loops, and performance monitoring for agentic systems in production.
Design and implement CI/CD pipelines for ML and GenAI systems.
Build infrastructure for model training, fine-tuning, evaluation, and deployment.
Develop reusable internal AI SDKs, templates, and tooling to accelerate development across teams.
Automate infrastructure provisioning using Infrastructure as Code (IaC).
Ensure high availability, scalability, cost optimization, and security of AI workloads.
Deploy and manage cloud-native AI workloads across AWS, Azure, or GCP.
Implement monitoring, logging, and alerting frameworks for AI systems.
Optimize GPU/accelerated workloads for performance and cost efficiency.
Expertise in Prometheus, Loki, Grafana, Kibana, Open Telemetry and other observability tools will be a plus.
Partner with Data Science and Engineering teams to productionize ML and GenAI solutions.
Work closely with business teams to deploy AI use cases tied to KPIs such as predictive maintenance, process optimization, and engineering productivity.

Qualifications

8–12+ years of professional experience in software engineering with Agentic AI, ML platform engineering.
BS/MS in Computer Science, Electrical Engineering, Data Science, or related field.
3+ years of hands-on experience with Generative AI and LLM-based systems in production environments.
Proven experience deploying ML/LLM systems with cloud-native infrastructure.

Technical Expertise

Strong programming skills in Python.
Experience with LLM frameworks (LangChain, LlamaIndex, Semantic Kernel, or similar).Deep understanding of RAG architectures and vector databases (PG vector, Milvus, FAISS, Pinecone, Weaviate, etc.).
CI/CD tools (GitHub Actions, GitLab CI, Jenkins, ArgoCD).
Cloud platforms (AWS, Azure, or GCP). Experience with MLOps tools (MLflow, Kubeflow, SageMaker, Vertex AI, etc.).Observability tools (Prometheus, Grafana, Open-Telemetry, etc.).

Preferred

Exposure to manufacturing, semiconductor, or high-tech enterprise environments.
Experience optimizing inference workloads (GPU, model quantization, batching strategies).
Familiarity with security, compliance, and governance frameworks for enterprise AI.
Contributions to internal AI platforms or developer productivity tooling.